Research Paper Cockpit

Research Track A

Papers on learning and model adaptation methods.

Daily Archives

Quick jump into generated daily digests.

Research Workflow

Latest digest: 2026-07-04.

Papers

337 visible entries

arxiv Score 37.0

Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management

2026-06-29 · Byeong Hoon Yoon

Research Track A · General AI

We introduce Neural Subspace Reallocation (NSR), which reframes continual learning as memory management over parameter subspaces. Instead of treating Low-Rank Adaptation (LoRA) modules as disposable per-task adapters, NSR manages them as compressible, retrievable memory units on a frozen backbone through a recurring cy…

Review
pending
Role
unreviewed
Read
now
arxiv Score 36.4

RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models

2026-06-22 · Ulas Berk Karli, Tesca Fitzgerald

Research Track A · General AI

Vision-Language-Action (VLA) models are commonly fine-tuned through passive imitation learning, where additional demonstrations are collected for tasks where the policy performs poorly. This approach incurs several downsides: it requires the robot to fail before data collection is triggered, provides little guidance ab…

Review
pending
Role
unreviewed
Read
now
arxiv Score 35.0

Lifelong Learning in Vision-Language Models: Enhanced EWC with Cross-Modal Knowledge Retention

2026-05-12 · Hamza Ahmed Durrani, Rafay Suleman Durrani

Research Track A · General AI

Large language-vision models (LVLMs) such as CLIP, Flamingo, and BLIP have revolutionized AI by enabling understanding across textual and visual modalities. These models excel at tasks like image captioning, visual question answering, and cross-modal retrieval. However, they face catastrophic forgetting when learning n…

Review
pending
Role
unreviewed
Read
now
arxiv Score 34.5

Modular Continual Learning via Zero-Leakage Reconstruction Routing and Autonomous Task Discovery

2026-04-15 · Noureddine Kermiche

Research Track A · General AI

Catastrophic forgetting remains a primary hurdle in sequential task learning for artificial neural networks. We propose a silicon-native modular architecture that achieves structural parameter isolation using Task-Specific Experts and a distributed, outlier-based Gatekeeper. Moving beyond traditional sequential consoli…

Review
pending
Role
unreviewed
Read
now
arxiv Score 30.0

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning

2026-03-12 · Jiaheng Hu, Jay Shim, Chen Tang, Yoonchang Sung, Bo Liu, Peter Stone, Roberto Martin-Martin

Research Track A · General AI

Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving environments. However, conventional wisdom from continual learning suggests that naive Sequential Fine-Tuning (Seq. FT) leads to catastrophi…

Review
pending
Role
unreviewed
Read
now
arxiv Score 29.5

The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical Reasoning

2026-06-05 · Rahul Nair, Chun Tao

Research Track A · General AI

Deploying Small Language Models (SLMs) on edge devices requires efficient fine-tuning strategies that adapt models to new tasks without degrading their general capabilities. In this study, we benchmark five sub-1B models (135M-1B) on mathematical reasoning tasks and uncover a critical vulnerability: Full Fine-Tuning (F…

Review
pending
Role
unreviewed
Read
now
arxiv Score 29.0

JumpLoRA: Sparse Adapters for Continual Learning in Large Language Models

2026-04-17 · Alexandra Dragomir, Ioana Pintilie, Antonio Barbalau, Marius Dragoi, Florin Brad, Cristian Daniel Paduraru, Alexandru Tifrea, Elena Burceanu, Radu Tudor Ionescu

Research Track A · General AI

Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-rank update matrix for each task. To mitigate catastrophic forgetting, state-of-the-art approaches impose constraints on new adapters with respect to the previous ones,…

Review
pending
Role
unreviewed
Read
now
arxiv Score 27.5

FOGO: Forgetting-aware Orthogonalization Optimizer

2026-06-09 · Toan Nguyen, Yang Liu, Trung Le, Celso de Melo, Flora D. Salim

Research Track A · General AI

We argue that forgetting is not confined to continual learning but is a general optimization phenomenon: during standard training, dominant mini-batch gradients suppress rare but useful update directions, causing short-term forgetting at every step. When such knowledge is never revisited, these losses compound into lon…

Review
pending
Role
unreviewed
Read
now
arxiv Score 27.0

Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation

2026-06-29 · Bertram Taetz, Hugo Albuquerque Cosme da Silva, Gabriele Bleser-Taetz

Research Track A · General AI

Motion-language agents must possess the bidirectional capability to both understand human movement (motion-to-text, M2T) and generate it from natural language (text-to-motion, T2M). While foundational models have achieved strong performance in static settings, autonomous agents operating in dynamic environments must co…

Review
pending
Role
unreviewed
Read
now
arxiv Score 26.0

Low-Rank Adaptation Reduces Catastrophic Forgetting in Sequential Transformer Encoder Fine-Tuning: Controlled Empirical Evidence and Frozen-Backbone Representation Probes

2026-03-29 · Ashish Pandey

Research Track A

Sequential fine-tuning of pretrained language encoders often overwrites previously acquired capabilities, but the forgetting behavior of parameter-efficient updates remains under-characterized. We present a controlled empirical study of Low-Rank Adaptation (LoRA) in sequential transformer encoder fine-tuning with compa…

Review
pending
Role
unreviewed
Read
now
arxiv Score 25.9

Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention

2026-06-24 · Luke McDermott, Robert W. Heath, Rahul Parhi

Research Track A · General AI

Lifelong continual learning remains an obstacle on the path to human-like intelligence. Modern transformers show sparks of intelligence with in-context learning. The quadratic nature of attention, however, prohibits transformers from performing this process on arbitrarily long sequences. In this work, we argue that ext…

Review
pending
Role
unreviewed
Read
now
arxiv Score 25.5

HiP-LoRA: Budgeted Spectral Plasticity for Robust Low-Rank Adaptation

2026-04-20 · Lixian Chen, Jianhong Tan

Research Track A

Adapting foundation models under resource budgets relies heavily on Parameter-Efficient Fine-Tuning (PEFT), with LoRA being a standard modular solution. However, LoRA suffers from spectral interference. Low-rank updates often concentrate energy on the leading singular directions of pretrained weights, perturbing genera…

Review
pending
Role
unreviewed
Read
now
arxiv Score 25.0

Towards Lifelong Aerial Autonomy: Geometric Memory Management for Continual Visual Place Recognition in Dynamic Environments

2026-04-10 · Xingyu Shao, Zhiqiang Yan, Liangzheng Sun, Mengfan He, Chao Chen, Jinhui Zhang, Chunyu Li, Ziyang Meng

Research Track A · General AI

Robust geo-localization in changing environmental conditions is critical for long-term aerial autonomy. While visual place recognition (VPR) models perform well when airborne views match the training domain, adapting them to shifting distributions during sequential missions triggers catastrophic forgetting. Existing co…

Review
pending
Role
unreviewed
Read
now
arxiv Score 25.0

Temporal Taskification in Streaming Continual Learning: A Source of Evaluation Instability

2026-04-23 · Nicolae Filat, Ahmed Hussain, Konstantinos Kalogiannis, Elena Burceanu

Research Track A · General AI

Streaming Continual Learning (CL) typically converts a continuous stream into a sequence of discrete tasks through temporal partitioning. We argue that this temporal taskification step is not a neutral preprocessing choice, but a structural component of evaluation: different valid splits of the same stream can induce d…

Review
pending
Role
unreviewed
Read
now
arxiv Score 25.0

PRISM: Exposing and Resolving Spurious Isolation in Federated Multimodal Continual Learning

2026-05-01 · Beining Wu, Zihao Ding, Jun Huang

Research Track A · General AI

While current federated multimodal continual learning over mixture-of-experts low-rank adaptation (MoE-LoRA) is built on the unverified assumption that routing isolates task-specific knowledge into disjoint experts, we argue that routing operates per-sample, while forgetting accumulates across the task sequence, and gr…

Review
pending
Role
unreviewed
Read
now
arxiv Score 25.0

CLaaS: Continual learning as a service for sample efficient online learning

2026-06-04 · Kion Fallah, Silen Naihin, Barak Widawsky, Qingqing Mao

Research Track A · General AI

Deployed large language model agents must adapt to distribution shift in dynamic environments. Ideally, adaptation can be performed from accumulated agent experiences and retain prior capabilities while transferring to future tasks. However, agent actions and environmental transitions can only be sampled once per scena…

Review
pending
Role
unreviewed
Read
now
arxiv Score 24.5

Parametric Skills

2026-06-29 · Xuan Zhao, Haonan He, Qingyu Yang, Minglei Li, Jingqi Ye, Zelin Tan, Bo Wan, Peng Ye

Research Track A · General AI

Since intelligence fundamentally relies on efficient skill acquisition (Chollet, 2019), the ability to leverage skills is critical. For LLMs, skills, manually authored or extracted from task trajectories, are textual recipes encoding mature problem-solving experience and are critical to agentic capabilities. Despite wi…

Review
pending
Role
unreviewed
Read
now
arxiv Score 24.4

MixedPEFT: Combining Multiple PEFT Methods with Mixed Objectives for Unsupervised Domain Adaptation

2026-06-20 · Mohammed Rawhani, Dervis Karaboga, Ozkan Ufuk Nalbantoglu, Alper Basturk, Bahriye Akay

Research Track A · General AI

Pre-trained language models struggle when applied to new domains, as full fine-tuning is computationally expensive and prone to catastrophic forgetting. This study addresses this challenge by presenting a novel parameter-efficient strategy for unsupervised domain adaptation that combines custom PEFT architectures with …

Review
pending
Role
unreviewed
Read
now
arxiv Score 24.0

Universe Routing: Why Self-Evolving Agents Need Epistemic Control

2026-03-16 · Zhaohui Geoffrey Wang

Research Track A · General AI

A critical failure mode of current lifelong agents is not lack of knowledge, but the inability to decide how to reason. When an agent encounters "Is this coin fair?" it must recognize whether to invoke frequentist hypothesis testing or Bayesian posterior inference - frameworks that are epistemologically incompatible. M…

Review
pending
Role
unreviewed
Read
now
arxiv Score 24.0

Face-D(^2)CL: Multi-Domain Synergistic Representation with Dual Continual Learning for Facial DeepFake Detection

2026-04-09 · Yushuo Zhang, Yu Cheng, Yongkang Hu, Jiuan Zhou, Jiawei Chen, Yuan Xie, Zhaoxia Yin

Research Track A

The rapid advancement of facial forgery techniques poses severe threats to public trust and information security, making facial DeepFake detection a critical research priority. Continual learning provides an effective approach to adapt facial DeepFake detection models to evolving forgery patterns. However, existing met…

Review
pending
Role
unreviewed
Read
now
arxiv Score 24.0

Continual Calibration: Coverage Can Collapse Before Accuracy in Lifelong LLM Fine-Tuning

2026-04-27 · Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

Research Track A · General AI

Continual learning for large language models is typically evaluated through accuracy retention under sequential fine-tuning. We argue that this perspective is incomplete, because uncertainty reliability can degrade earlier and more sharply than top-1 performance. We study this empirically by measuring conformal coverag…

Review
pending
Role
unreviewed
Read
now
arxiv Score 23.9

CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift

2026-06-22 · Amrita Singh, Rishabh Jha

Research Track A

Medical vision-language models (VLMs) such as BiomedCLIP generalize broadly, but adapting them to a clinical service is as much a safety problem as an accuracy one. Updating a deployed model for a new imaging modality can fail silently in two ways that harm patients: it can forget modalities it already handled (catastr…

Review
pending
Role
unreviewed
Read
now
arxiv Score 23.8

STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?

2026-05-07 · Hanxiang Chao, Yihan Bai, Rui Sheng, Tianle Li, Yushi Sun

Research Track A · General AI

Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new evidence emerges. We identify a critical and underexplored failure mode, Implicit Con…

Review
pending
Role
unreviewed
Read
now
arxiv Score 23.5

Fact4ac at the Financial Misinformation Detection Challenge Task: Reference-Free Financial Misinformation Detection via Fine-Tuning and Few-Shot Prompting of Large Language Models

2026-04-16 · Cuong Hoang, Le-Minh Nguyen

Research Track A · General AI

The proliferation of financial misinformation poses a severe threat to market stability and investor trust, misleading market behavior and creating critical information asymmetry. Detecting such misleading narratives is inherently challenging, particularly in real-world scenarios where external evidence or supplementar…

Review
pending
Role
unreviewed
Read
now
arxiv Score 23.3

A History-Aware Visually Grounded Critic for Computer Use Agents

2026-06-09 · Jaewoo Lee, Zaid Khan, Archiki Prasad, Justin Chih-Yao Chen, Supriyo Chakraborty, Kartik Balasubramaniam, Sambit Sahu, Elias Stengel-Eskin, Hyunji Lee, Mohit Bansal

Research Track A · Research Track B · General AI

Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in complex Graphical User Interface (GUI) environments. However, existing critics suffer from two key limitations: they (1) focus primarily on short…

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.5

Continual Learning in Large Language Models: Methods, Challenges, and Opportunities

2026-03-13 · Hongyang Chen, Zhongwu Sun, Hongfei Ye, Kunchi Li, Xuemin Lin

Research Track A · General AI

Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static pre-training paradigm inherent to modern LLMs. This survey presents a comprehensiv…

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.5

Temporal Memory for Resource-Constrained Agents: Continual Learning via Stochastic Compress-Add-Smooth

2026-03-31 · Michael Chertkov

Research Track A · General AI

An agent that operates sequentially must incorporate new experience without forgetting old experience, under a fixed memory budget. We propose a framework in which memory is not a parameter vector but a stochastic process: a Bridge Diffusion on a replay interval $[0,1]$, whose terminal marginal encodes the present and …

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.5

Information as Structural Alignment: A Dynamical Theory of Continual Learning

2026-04-08 · Radu Negulescu

Research Track A · General AI

Catastrophic forgetting is not an engineering failure. It is a mathematical consequence of storing knowledge as global parameter superposition. Existing methods, such as regularization, replay, and frozen subnetworks, add external mechanisms to a shared-parameter substrate. None derives retention from the learning dyna…

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.5

BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning

2026-04-14 · Jagadeesh Rachapudi, Ritali Vatsi, Praful Hambarde, Amit Shukla

Research Track A · General AI

Recent advances in deep learning underscore the need for systems that can not only acquire new knowledge through Continual Learning (CL) but also remove outdated, sensitive, or private information through Machine Unlearning (MU). However, while CL methods are well-developed, MU techniques remain in early stages, creati…

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.5

TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning

2026-04-28 · Dominik Żurek, Kamil Faber, Marcin Pietron, Paweł Gajewski, Roberto Corizzo

Research Track A · General AI

Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on previously learned tasks. This setting corresponds to domains where new tasks arise over time, but adapting the model in live environment interactions is expensive, risky, …

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.3

Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning Agents

2026-06-03 · Bo Mao, Jie Zhou, Yutao Yang, Xin Li, Xian Wei, Qin Chen, Xingjiao Wu, Liang He

Research Track A · General AI

Lifelong learning is essential for Large Language Model (LLM) agents operating in dynamic, interactive environments. However, existing lifelong learning agents for long-horizon tasks typically depend on discrete skill or past experiences retrieval with static parameters during inference, which prevents them from contin…

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.3

Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails

2026-07-02 · Qianyu Chen, Canran Xiao, Runxuan Tang

Research Track A · General AI

Multimodal large language models must continually adapt to evolving tasks and domains, yet standard continual learning metrics mainly measure whether old answers remain correct, leaving the stability of multimodal grounding largely unexamined. We study this overlooked failure mode and ask whether a continually adapted …

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.2

TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory

2026-06-23 · Tianyu Yang, Sudipta Paul, Vijay Srinivasan, Vivek Kulkarni, Srinivas Chappidi

Research Track A · General AI

Large language model (LLM) agents rely on long-term memory to support extended interactions and personalized assistance beyond finite context windows. Existing memory agents actively update external memory through generated write, revise, and delete operations, but these updates may omit important information, corrupt …

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.0

Learning, Fast and Slow: Towards LLMs That Adapt Continually

2026-05-12 · Rishabh Tiwari, Kusha Sareen, Lakshya A Agrawal, Joseph E. Gonzalez, Matei Zaharia, Kurt Keutzer, Inderjit S Dhillon, Rishabh Agarwal, Devvrit Khatri

Research Track A · General AI

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of plasticity. In contrast, in-context learning with fixed LLM parameters can chea…

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.0

Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning

2026-05-27 · Cheng Chen, Pengpeng Zeng, Yuyu Guo, Lianli Gao, Hengtao Shen, Jingkuan Song

Research Track A · General AI

Low-Rank Adaptation (LoRA) has emerged as a promising paradigm for Continual Learning. It independently updates its low-rank factors ($A$ and $B$), creating a composite update to the full weight matrix through their interaction. To prevent catastrophic forgetting, this update should remain orthogonal to the task-specif…

Review
pending
Role
unreviewed
Read
now
arxiv Score 22.0

Evaluating the Impact of Task Granularity on Catastrophic Forgetting in Continual Learning

2026-06-06 · Emre Alyamac, Himanshu Janmeda, Shashwat Krishna, Yash Vijay

Research Track A

Catastrophic forgetting, the abrupt loss of previously acquired knowledge upon learning new information, remains the central challenge in Continual Learning. This project investigates whether the order in which a model learns information affects how well it retains knowledge. Specifically, we ask: does learning general…

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.5

Improving Sparse Memory Finetuning

2026-04-06 · Satyam Goyal, Anirudh Kanchi, Garv Shah, Prakhar Gupta

Research Track A · General AI

Large Language Models (LLMs) are typically static after training, yet real-world applications require continual adaptation to new knowledge without degrading existing capabilities. Standard approaches to updating models, like full finetuning or parameter-efficient methods (e.g., LoRA), face a fundamental trade-off: cat…

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.5

Balancing Stability and Plasticity in Sequentially Trained Early-Exiting Neural Networks

2026-05-06 · Alaa Zniber, Ouassim Karrakchou, Mounir Ghogho

Research Track A · General AI

Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by incrementally adding them to a shared backbone; however, this sequential training can c…

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.5

Online Continual Learning with Dynamic Label Hierarchies

2026-05-12 · Xinrui Wang, Shao-Yuan Li, Bartłomiej Twardowski, Alexandra Gomez-Villa, Songcan Chen

Research Track A · General AI

Online Continual Learning (OCL) aims to learn from endless non\text{-}stationary data streams, yet most existing methods assume a flat label space and overlook the hierarchical organization of real\text{-}world concepts that evolves both horizontally (sibling classes) and vertically (coarse or fine categories). To bett…

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.5

Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning

2026-05-12 · Patryk Krukowski, Jacek Tabor, Przemysław Spurek, Marek Śmieja, Łukasz Struski

Research Track A · General AI

Data-free continual learning (DFCIL) relies on model inversion to synthesize pseudo-samples and mitigate catastrophic forgetting. However, existing inversion methods are fundamentally limited by a simplifying assumption: they model feature distributions using diagonal covariance, effectively ignoring correlations that …

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.5

SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation

2026-05-21 · Javad Parsa, Enis Simsar, Amir Joudaki, Thomas Hofmann, André M. H. Teixeira

Research Track A · General AI

Parameter-efficient fine-tuning enables fast personalization of text-to-image diffusion models, but composing multiple custom concepts remains challenging due to representation interference. Existing modular methods either rely on expensive post-hoc fusion or freeze adaptation subspaces, which limit expressiveness and …

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.5

Parameter-Efficient Continual Learning for Automatic Speech Recognition

2026-06-08 · Steven Vander Eeckt, Hugo Van hamme

Research Track A

Speech foundation models enable strong general-purpose ASR and are attractive for downstream adaptation. However, their size and the catastrophic forgetting induced by sequential fine-tuning demand parameter-efficient and regularized training methods, motivating parameter-efficient continual learning (PECL). While PECL…

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.5

The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning

2026-06-29 · Yiting Hu, Lingjie Duan, Qian Zhang

Research Track A

Machine unlearning aims to eliminate the influence of specific data from trained models to safeguard privacy. However, this presents a significant challenge in the context of continual learning (CL), where models update sequentially on dynamic datasets. A major limitation is that current certified unlearning algorithms…

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.3

Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games

2026-06-17 · Shengyuan Ding, Xilin Wei, Xinyu Fang, Haodong Duan, Dahua Lin, Jiaqi Wang, Yuhang Zang

Research Track A · General AI

Deploying multimodal foundation models as closed-loop policies increasingly requires conditioning actions on observations that are no longer visible. However, existing benchmarks either expose the full state, conflate hidden-state reconstruction with other agent skills, or test recall only after an episode has ended. W…

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.2

Are We Ready For An Agent-Native Memory System?

2026-06-23 · Wei Zhou, Xuanhe Zhou, Shaokun Han, Hongming Xu, Guoliang Li, Zhiyu Li, Feiyu Xiong, Fan Wu

Research Track A · General AI

Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports persistent information storage, retrieval, update, consolidation, and dynamic lifecycle governance throughout agent execution. Despite this evolution, existing evaluati…

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.0

COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling

2026-04-22 · Noah Flynn

Research Track A · General AI

Large language models (LLMs) often exhibit performance disparities across languages, with naive multilingual fine-tuning frequently degrading performance due to negative cross-lingual interference. To address this, we introduce COMPASS (COntinual Multilingual PEFT with Adaptive Semantic Sampling), a novel data-centric …

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.0

Learning What to Remember: A Cognitively Grounded Multi-Factor Value Model for Agentic Memory

2026-06-11 · Zhibao Chen, Qian Cheng

Research Track A · General AI

Long-running LLM agents accumulate interaction histories far larger than any context window, forcing a standing decision: what to encode deeply, what to forget, and what to retrieve under a fixed memory budget. Production systems answer with semantic similarity or recency -- both mis-specified for the forgetting decisi…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.5

Cortex-Inspired Continual Learning: Unsupervised Instantiation and Recovery of Functional Task Networks

2026-04-27 · Kevin McKee, Thomas Hazy, Yicong Zheng, Zacharie Bugaud, Thomas Miconi

Research Track A · General AI

Block-sequential continual learning demands that a single model both protect prior solutions from catastrophic forgetting and efficiently infer at inference time which prior solution matches the current input without task labels. We present Functional Task Networks (FTN), a parameter-isolation method inspired by struct…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.5

Understanding Generalization and Forgetting in In-Context Continual Learning

2026-05-27 · Guangyu Li, Meng Ding, Lijie Hu

Research Track A · General AI

In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter updates. Existing theories primarily study ICL in single-task settings, while real-world prompts often contain sequences of heterogeneous task…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.3

CL-VISTA: Benchmarking Continual Learning in Video Large Language Models

2026-04-01 · Haiyang Guo, Yichen Shi, Fei Zhu, Wenzhuo Liu, Hongbo Zhao, Fanhu Zeng, Shijie Ma, Da-Han Wang, Xu-Yao Zhang

Research Track A · General AI

Video Large Language Models (Video-LLMs) require continual learning to adapt to non-stationary real-world data. However, existing benchmarks fall short of evaluating modern foundation models: many still rely on models without large-scale pre-training, and prevailing benchmarks typically partition a single dataset into …

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.3

MA-IDS: Multi-Agent RAG Framework for IoT Network Intrusion Detection with an Experience Library

2026-04-07 · Md Shamimul Islam, Luis G. Jaimes, Ayesha S. Dina

Research Track A · General AI

Network Intrusion Detection Systems (NIDS) face important limitations. Signature-based methods are effective for known attack patterns, but they struggle to detect zero-day attacks and often miss modified variants of previously known attacks, while many machine learning approaches offer limited interpretability. These …

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.3

GAM: Hierarchical Graph-based Agentic Memory for LLM Agents

2026-04-14 · Zhaofen Wu, Hanrong Zhang, Fulin Lin, Wujiang Xu, Xinran Xu, Yankai Chen, Henry Peng Zou, Shaowen Chen, Weizhi Zhang, Xue Liu, Philip S. Yu, Hongwei Wang

Research Track A · General AI

To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current unified stream-based memory systems facilitate context updates but remain vulnerable to interference from transient noise. Conversely, discrete…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.3

LUNA-AD: Lightweight Uncertainty-Aware Language Model with Lifelong Learning for Autonomous Driving

2026-06-07 · Ruoyu Yao, Pei Liu, Ruiguo Zhong, Mingxing Peng, Rui Yang, Jun Ma

Research Track A · General AI

While large language models (LLMs) offer promising reasoning capabilities, their integration into safety-critical driving systems is hindered by limited reasoning diversity, high computational overhead, and static learning paradigms. To address these challenges, we propose LUNA-AD, a lightweight uncertainty-aware langu…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.0

Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights

2026-04-19 · Liangzu Peng, Uday Kiran Reddy Tadipatri, Ziqing Xu, Eric Eaton, René Vidal

Research Track A · General AI

Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years, the theoretical development of CL remains in its infancy. At the heart of developing CL theory lies the challenge that the data distributi…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.0

FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory

2026-04-22 · Yingjie Gu, Bo Xiong, Yijuan Guo, Chao Li, Xiaojing Zhang, Liqiang Wang, Pengcheng Ren, Qi Sun, Jingyao Ma, Shidang Shi

Research Track A · General AI

For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive processes (hippocampal indexing/consolidation theory and Ebbinghaus forgetting curve)--remains underexplored. We argue that in resource-cons…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.0

HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search

2026-05-03 · Matteo Gambella, Fabrizio Pittorino, Manuel Roveri

Research Track A · General AI

Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and efficiency. However, as AI transitions from static benchmarks to real-world deployment, the traditional focus on hardware-aware efficiency is no longer sufficient. We observe…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.0

CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning

2026-05-07 · Md Anwar Hossen, Fatema Siddika, Juan Pablo Munoz, Tanya Roosta, Ali Jannesari

Research Track A · General AI

Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learning framework that avoids updating model weights by instead learning low-rank interventions on hidden representations. CRAFT proceeds in thre…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.9

The Gentle Collapse: Distributional Metrics for Continual Learning

2026-06-23 · Ahmed Anwar, Andreas Wagner, Federico Raue, Tobias Nauen, Andreas Dengel

Research Track A

Accuracy degradation is the standard metric for Catastrophic Forgetting (CF), however, it records only whether forgetting occurred or not. It saturates at the extremes and collapses discretely at task boundaries, hiding the internal structure of what is being forgotten. We introduce six softmax-derived metrics spanning…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.8

MemGym: a Long-Horizon Memory Environment for LLM Agents

2026-05-20 · Wujiang Xu, Yu Wang, Kai Mei, Kaiqu Liang, Zhenting Wang, Mingyu Jin, Han Zhang, Shi-Xiong Zhang, Wenyue Hua, Sambit Sahu, Dimitris N. Metaxas

Research Track A · Research Track B · General AI

Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory formation that occurs during extended agent execution. Consequently, the memory systems …

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.5

Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair

2026-04-24 · Yuelin Hu, Zhenbo Yu, Zhengxue Cheng, Wei Liu, Li Song

Research Track A · General AI

Many continual-learning methods modify gradients upstream (e.g., projection, penalty rescaling, replay mixing) while treating Adam as a neutral backend. We show this composition has a hidden failure mode. In a high-overlap, non-adaptive 8-domain continual LM, all shared-routing projection baselines collapse close to va…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.5

Attribution-Guided Continual Learning for Large Language Models

2026-05-06 · Yazheng Liu, Yuxuan Wan, Rui Xu, Xi Zhang, Sihong Xie, Hui Xiong

Research Track A · General AI

Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing methods mitigate catastrophic forgetting by data replay, parameter freezing, or regularization. However, these methods lack semantic awarenes…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.5

Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments

2026-06-04 · Parth Asawa, Christopher M. Glaze, Gabriel Orlanski, Ramya Ramakrishnan, Benji Xu, Asim Biswal, Vincent Sunn Chen, Frederic Sala, Matei Zaharia, Joseph E. Gonzalez

Research Track A · General AI

Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchmark exists to evaluate it. We introduce Continual Learning Bench (CL-Bench), the first difficult, expert-validated benchmark designed to measure whether LLM-based systems…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.5

Social World Model for Lifelong Social Intelligence

2026-06-19 · Yu Luo

Research Track A · General AI

Social intelligence is a core competency for language agents, yet current research primarily focuses on static capability evaluation rather than how these skills are continuously shaped and accumulated. This gap calls for a shift toward sustainable learning paradigms. Currently, two methodological pain points exist: so…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.4

LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective

2026-06-24 · Zhihao Gu, Lin Wang

Research Track A · General AI

Building a generalist robot that can leverage prior knowledge for continuous task adaptation remains a significant challenge. Previous works alleviate the catastrophic forgetting problem by parameter-efficient fine-tuning for single-task adaptation. However, they fail to extract reusable skills and model the interactio…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.3

From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents

2026-04-21 · Md Nayem Uddin, Kumar Shubham, Eduardo Blanco, Chitta Baral, Gengyu Wang

Research Track A · General AI

Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks predominantly frame long-term memory evaluation as fact retrieval from past conversations, providing limited insight into agents' ability to …

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.0

FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation

2026-03-30 · Tiantian Wang, Xiang Xiang, Simon S. Du

Research Track A · General AI

In federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, enabling continuous adaptive model learning among distributed clients while safeguarding data privacy. However, in practical applications, data across agent nodes within the distributed framework often exhibits n…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.0

Task Switching Without Forgetting via Proximal Decoupling

2026-04-20 · Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, William A. P. Smith, Yue Lu

Research Track A · General AI

In continual learning, the primary challenge is to learn new information without forgetting old knowledge. A common solution addresses this trade-off through regularization, penalizing changes to parameters critical for previous tasks. In most cases, this regularization term is directly added to the training loss and o…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.0

Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization

2026-06-03 · Jiahua Dong, Wenqi Liang, Hongliu Li, Yang Cong, Duzhen Zhang, Hanbin Zhao, Henghui Ding, Yulun Zhang, Salman Khan, Fahad Shahbaz Khan

Research Track A · General AI

Custom diffusion models (CDMs) have garnered significant interest owing to their remarkable capacity for generating personalized concepts. However, the majority of CDMs unrealistically presume that the user's collection of personalized concepts is static and incapable of incremental growth over time. Furthermore, they …

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.0

Bridging Geographic Bias in Urban Streetscape Inference via Lifelong Learning with Visual-Semantic Pivoting

2026-06-13 · Xinze Zhang

Research Track A · General AI

Visual perception of urban streetscapes underpins evidence-based decisions in landscape planning, public health, and place-making. Yet models trained on a few well-photographed metropolises systematically misjudge underrepresented districts, propagating geographic bias into downstream policy. We address this gap with H…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.0

KeepLoRA++: Continual Learning with Layer-Scaled Residual Gradient Adaptation

2026-06-15 · Mao-Lin Luo, Yi-Lin Zhang, Zi-Hao Zhou, Yankun Hong, Xialiang Tong, Mingxuan Yuan, Tong Wei, Min-Ling Zhang

Research Track A · General AI

Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of learned tasks, and maintaining the plasticity to acquire new knowledge. This paper presents KeepLoRA++, balancing these objectives through a u…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.9

Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs

2026-06-22 · Chuangxin Zhao, Canran Xiao, Siyuan Ma, Mengyao Lyu, Yanbiao Ma, Jun Xia, Guiguang Ding, Yang Liu

Research Track A · General AI

Multimodal large language models (MLLMs) are increasingly required to adapt to non-stationary streams of visual domains, question types, and user instructions, yet continual fine-tuning often causes severe forgetting of previously acquired multimodal skills. Existing continual vision-language methods mainly preserve ou…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.8

Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training

2026-07-02 · Meng Wang, Haohan Zhao, Wenzhuo Liu, Lu Yang, Geng Liu, Haiyang Guo, Guo-Sen Xie, Gaofeng Meng, Hongbin Liu, Fei Zhu

Research Track A · General AI

Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgetting, with on-policy self-distillation emerging as a particularly attractive approach. In this work, we revisit this optimistic view through …

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.5

Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics

2026-05-06 · Andreas Pattichis, Constantine Dovrolis

Research Track A · General AI

LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled multi-timescale dynamics make new associations immediately usable, strengthen wha…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.5

Joint sparse coding and temporal dynamics support context reconfiguration

2026-05-11 · Qianqian Shi, Yue Che, Faqiang Liu, Hongyi Li, Mingkun Xu, Sandra Reinert, Pieter M. Goltstein, Rong Zhao, Luping Shi

Research Track A

Adaptive behavior requires the brain to transition between distinct contexts while maintaining representations of prior experience. The ability to reconfigure neural representations without erasing previously acquired knowledge is central to learning in dynamic environments, yet the neural mechanisms that support this …

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.5

Learning When to Adapt

2026-05-18 · Ali Zindari, Xiaowen Jiang, Rotem Mulayoff, Sebastian U. Stich

Research Track A · General AI

Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method, yet its learned correction is static: the same low-rank update is applied to every input. This input-agnostic approach creates an inevitable compromise between adapting to the fine-tuning distribution and preserving pre-trained behavior…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.5

Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting

2026-05-28 · Runze Xu, Arpit Garg, Hemanth Saratchandran, Simon Lucey

Research Track A · General AI

Low-Rank Adaptation (LoRA) has become one of the most widely used fine-tuning mechanisms for adapting large language models to new domains, tasks, and users. Yet adaptation performance alone can obscure an important failure mode: LoRA updates may improve performance on the target distribution while degrading prior capa…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.5

Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data

2026-06-09 · Masoume Gholizade, Fabrizio Ruffini, Pietro Ducange, Francesco Marcelloni

Research Track A · General AI

Federated Learning (FL) enables collaborative and privacy-preserving model training across distributed clients, but most existing FL systems implicitly assume data stationarity. In real-world settings-such as healthcare, industrial IoT (IIOT), cybersecurity, and smart cities-data streams are inherently non-stationary, …

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.5

Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning

2026-06-14 · Shuaike Zhang, Shaokun Wang, Haoyu Tang, Jianlong Wu, Liqiang Nie

Research Track A · General AI

Embodied Continual Learning (ECL) aims to enable robots to continually acquire new manipulation tasks while retaining previously learned behaviors under closed-loop control. Compared with conventional continual learning, ECL suffers from more severe catastrophic forgetting. Feature drift accumulated under closed-loop c…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.3

ElephantBroker: A Knowledge-Grounded Cognitive Runtime for Trustworthy AI Agents

2026-03-26 · Cristian Lupascu, Alexandru Lupascu

Research Track A · General AI

Large Language Model based agents increasingly operate in high stakes, multi turn settings where factual grounding is critical, yet their memory systems typically rely on flat key value stores or plain vector retrieval with no mechanism to track the provenance or trustworthiness of stored knowledge. We present Elephant…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.0

CoMemNet: Contrastive Sampling with Memory Replay Network for Continual Traffic Prediction

2026-05-07 · Mei Wu, Wenchao Weng, Wenxin Su, Wenjie Tang, Wei Zhou

Research Track A · General AI

In recent years, the integration of non-topological space modeling with temporal learning methods has emerged as an effective approach for capturing spatio-temporal information in non-Euclidean graphs. However, most existing methods rely on static underlying graph structures, which are inadequate for capturing the cont…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.0

Consolidation-Expansion Operator Mechanics:A Unified Framework for Adaptive Learning

2026-05-11 · Debashis Guha

Research Track A · General AI

Every adaptive learning system must alternate between two operations: consolidating what it already knows and expanding into new evidence. We propose \emph{Consolidation-Expansion Operator Mechanics} (OpMech), a framework that makes this structure precise. The central object is the \emph{order-gap} $\Ogap(θ; e)$, the d…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.0

EVAF: A Test-Retest Protocol for Selective Parametric Consolidation

2026-06-29 · Haoliang Han

Research Track A · General AI

Long-running language agents need mechanisms for deciding which experiences should persist after the working context is gone. Retrieval systems can reinsert past text, but they do not by themselves show that an experience has been selectively consolidated into the model's own behavior. We introduce EVAF, an Echo-Valenc…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.9

Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory

2026-06-23 · Beining Wu, Zihao Ding, Jun Huang, Yanxiao Zhao

Research Track A · General AI

On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights. This memory is hard-bounded and exposed: it consumes RAM and energy, reaches peers through a thin uplink, and becomes an attack surface because it is writable by what the agent reads. Existing systems…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.8

Rethinking Memory as Continuously Evolving Connectivity

2026-05-27 · Jizhan Fang, Buqiang Xu, Zhixian Wang, Haoliang Cao, Xinle Deng, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu, Ying Wei, Guozhou Zheng, Feiyu Xiong, Haofen Wang, Huajun Chen, Ningyu Zhang

Research Track A · General AI

Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic environments where feedback, task variation, and heterogeneous signals continuously reshape what should be remembered and how it should be co…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.5

All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptation

2026-03-15 · Xudong Wang, Gan Li, Zhiyu Liu, Yao Wang, Lianqing Liu, Zhi Han

Research Track A · General AI

Deploying vision-and-language navigation (VLN) agents requires adaptation across diverse scenes and environments, but fine-tuning on a specific scenario often causes catastrophic forgetting in others, which severely limits flexible long-term deployment. We formalize this challenge as the all-day multi-scenes lifelong V…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.5

When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents

2026-04-29 · Qisheng Hu, Quanyu Long, Wenya Wang

Research Track A · General AI

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric learning. We show that this challenge does not disappear but resurfaces at the memory…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.5

Amnesia: A Stealthy Replay Attack on Continual Learning Dreams

2026-06-10 · Ahmed Sharshar, Naveen Kumar Kummari, Mohsen Guizani

Research Track A · General AI

Continual learning (CL) models often use experience replay to reduce catastrophic forgetting, but their robustness to replay sampling interference remains underexplored. Existing CL attacks alter inputs or training pipelines (poisoning/backdoors) and rarely include explicit auditable constraints, limiting realism. Here…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.5

Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation

2026-06-19 · Jianwei Lou

Research Track A · General AI

Continual learning that is gradient-free, local, online, and append-only is attractive for edge and streaming deployment, but its value is usually argued informally. We give a provable account on recurring-regime streams. Given segmentation, a warm-start library learner attains amortized recovery cost $O\!\big(KD/\vare…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.3

CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning

2026-04-12 · Cheng-Yen Li, Xuanjun Chen, Claire Lin, Wei-Yu Chen, Wenhua Nie, Hung-Yi Lee, Jyh-Shing Roger Jang

Research Track A · General AI

Large Language Models (LLMs) struggle with knowledge-intensive tasks due to hallucinations and fragmented reasoning over dispersed information. While Retrieval-Augmented Generation (RAG) grounds generation in external sources, existing methods often treat evidence as isolated units, failing to reconstruct the logical c…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.3

AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction

2026-04-18 · Pollawat Hongwimol, Haoning Shang, Chutong Wang, Zhichao Wan, Yi Gao, Yuanming Li, Lin Gui, Wenhao Sun, Cheng Yu

Research Track A · General AI

Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain. We present AutoPKG, a multi-agent Large Language Model (LLM) framework that automatically constructs a Product-attribute Knowledge Graph (PKG) from multimodal product content. AutoPKG indu…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.3

What Should a Streaming Video Model Remember?

2026-06-15 · Haonan Ge, Yiwei Wang, Hang Wu, Yujun Cai

Research Track A · General AI

Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under fixed memory and computation budgets. Existing methods address this by adding memory banks, retrieval modules, or visual token compression to preserve long-range history. …

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.0

MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models

2026-04-18 · Zhaokang Liao, Yingguo Gao, Yi Yang, Yongheng Hu, Jingting Ding

Research Track A · General AI

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising approach to improve the reasoning abilities of Large Language Models (LLMs). Among RLVR algorithms, Group Relative Policy Optimization (GRPO) and its variants have demonstrated strong performance and high training efficiency. However, GRPO…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.0

Forager: a lightweight testbed for continual learning with partial observability in RL

2026-05-01 · Steven Tang, Xinze Xiong, Anna Hakhverdyan, Andrew Patterson, Jacob Adkins, Jiamin He, Esraa Elelimy, Parham Mohammad Panahi, Martha White, Adam White

Research Track A · General AI

In continual reinforcement learning (CRL), good performance requires never-ending learning, acting, and exploration in a big, partially observable world. Most CRL experiments have focused on loss of plasticity -- the inability to keep learning -- in one-off experiments where some unobservable non-stationarity is added …

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.0

You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation

2026-05-06 · Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera, Stjepan Picek, Saraga Sakthidharan

Research Track A · General AI

The open-source ecosystem has accelerated the democratization of Large Language Models (LLMs) through the public distribution of specialized Low-Rank Adaptation (LoRA) modules. However, integrating these third-party adapters often induces catastrophic forgetting of the base model's foundational safety alignment. Restor…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.0

Theoretical Foundations of Continual Learning via Drift-Plus-Penalty

2026-06-07 · Nazreen Shah, Govinda Arya, Bharath B. N., Ranjitha Prasad

Research Track A · General AI

In many real-world settings, data streams are nonstationary and arrive sequentially, requiring learning systems to adapt continuously without retraining from scratch. Continual learning (CL) addresses this challenge by incorporating new tasks while mitigating catastrophic forgetting, where learning new information degr…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.0

TaskFusion: Continual Anomaly Detection for Heterogeneous Tabular Data

2026-06-10 · Dayananda Herurkar, Federico Raue, Joachim Folz, Jörn Hees, Andreas Dengel

Research Track A · General AI

Continual anomaly detection in tabular data is challenging and remains largely underexplored, particularly in settings with heterogeneous feature schemas, distribution shifts, and severe class imbalance. In many real-world applications, data arrive sequentially from diverse domains, rendering conventional continual lea…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.0

Continual Backdoor Training in IoT/CPS

2026-06-12 · Oxana Salish, Kuniyilh S

Research Track A

Internet of Things (IoT) and Cyber-physical systems (CPS) increasingly rely on continual learning (CL) to adapt to evolving environments, device heterogeneity, and concept drift, thereby improving overall utility. While continual adaptation is essential for long-lived IoT deployments where data patterns evolve, it also…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.0

Task-Differentiated Atomic Skill Expansion and Routing for Continual Learning Across Highly Heterogeneous Tasks

2026-06-19 · Jiacheng Wang, Xinjia He, Qi Ding, Yutao Yang, Jie Zhou, Liyang Yu, Liang Dou, Qin Chen

Research Track A · General AI

Continual learning (CL) is commonly studied under the assumption that sequential tasks are semantically related or structurally similar. However, in highly heterogeneous settings, where tasks differ substantially in reasoning patterns and input-output formats, existing methods often suffer from catastrophic forgetting …

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.8

Task-Focused Memorization for Multimodal Agents

2026-05-29 · Tao Zou, Yichen He, Tian Qiu, Yuan Lin, Hang Li

Research Track A · General AI

Long-term memory is essential for multimodal agents to build coherent experience, accumulate world knowledge, and achieve continual learning. However, constructing effective memory goes beyond memory module design and basic requirements such as accuracy and fidelity; the key challenge lies in determining what to memori…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.5

SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

2026-04-06 · Varun Pratap Bhardwaj

Research Track A · General AI

AI coding agents operate in a paradox: they possess vast parametric knowledge yet cannot remember a conversation from an hour ago. Existing memory systems store text in vector databases with single-channel retrieval, require cloud LLMs for core operations, and implement none of the cognitive processes that make human m…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.5

In-Place Test-Time Training

2026-04-07 · Guhao Feng, Shengjie Luo, Kai Hua, Ge Zhang, Di He, Wenhao Huang, Tianle Cai

Research Track A · General AI

The static ``train then deploy" paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new information inherent in real-world tasks. Test-Time Training (TTT) offers a compelling alternative by updating a subset of model parameters (fast we…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.5

ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems

2026-04-26 · Alexander Bering

Research Track A · General AI

Despite a century of empirical memory research, existing AI agent memory systems rely on system-engineering metaphors (virtual-memory paging, flat LLM storage, Zettelkasten notes), none integrating principles of consolidation, forgetting, and reconsolidation. We present ZenBrain, a multi-layer memory architecture integ…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.5

MPCS: Neuroplastic Continual Learning via Multi-Component Plasticity and Topology-Aware EWC

2026-05-04 · Joern Hentsch

Research Track A · General AI

Continual learning systems face a fundamental tension between plasticity -- acquiring new knowledge -- and stability -- retaining prior knowledge. We introduce MPCS (Multi-Plasticity Continual System), a neuroplastic architecture that integrates eleven complementary mechanisms: task-driven neurogenesis, Fourier-encoded…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.5

Intrinsic Vicarious Conditioning for Deep Reinforcement Learning

2026-05-12 · Rodney A Sanchez, Ferat Sahin, Alex Ororbia, Jamison Heard

Research Track A · General AI

Advancements in reinforcement learning have produced a variety of complex and useful intrinsic driving forces; crucially, these drivers operate under a direct conditioning paradigm. This form of conditioning limits our agents' capacity by restricting how they learn from the environment as well as from others. Off-polic…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.5

Dynamic Mixture of Latent Memories for Self-Evolving Agents

2026-05-21 · Dianzhi Yu, Vireo Zhang, Hongru Wang, Yanyu Chen, Minda Hu, Wanghan Xu, Siki Chen, Philip Torr, Zhenfei Yin, Irwin King

Research Track A · General AI

Achieving self-evolution in intelligent agents requires the continual accumulation of new knowledge across changing task sequences without forgetting previously acquired abilities. Existing approaches either internalize knowledge by updating model parameters, which induces catastrophic forgetting, or rely on external m…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.5

Active Continual Learning with Metaplastic Binary Bayesian Neural Networks

2026-05-28 · Kellian Cottart, Théo Ballet, Djohan Bonnet, Damien Querlioz

Research Track A · General AI

Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. Bayesian binary neural networks are attractive in this setting, but mean-field Bernoulli posteriors can saturate on long non-stationary streams, wiping out epistemic uncertainty and freezin…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.5

Not Just After One: Sleep-Inspired Replay Prevents Catastrophic Forgetting After Sequential Tasks

2026-06-07 · Anthony Bazhenov, Jean Erik Delanois, Giri P. Krishnan

Research Track A

One of the critical limitations of artificial neural networks is their lack of ability to continually learn: training on new tasks often leads to interference and forgetting of the previous ones. While several algorithms have been proposed to protect old memories from interference, they are typically applied during or …

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.5

Medical Heuristic Learning: An LLM-Driven Framework for Interpretable and Auditable Clinical Decision Rules

2026-06-15 · Wei Xu, Ke Yang, Gang Luo, Keli Zheng, Lingyan Hu, Jing Wang, Kefeng Li

Research Track A · General AI

Predictive modeling for clinical tabular data is central to clinical decision support and therefore requires not only strong predictive performance but also transparent decision logic. Although deep learning and tree-based ensemble methods can achieve high accuracy, their black-box nature remains a major obstacle to cl…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.3

An Empirical Study of Multi-Agent Collaboration for Automated Research

2026-03-31 · Yang Shen, Zhenyi Yi, Ziyi Zhao, Lijun Sun, Dongyang Li, Chin-Teng Lin, Yuhui Shi

Research Track A · General AI

As AI agents evolve, the community is rapidly shifting from single Large Language Models (LLMs) to Multi-Agent Systems (MAS) to overcome cognitive bottlenecks in automated research. However, the optimal multi-agent coordination framework for these autonomous agents remains largely unexplored. In this paper, we present …

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.3

Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge

2026-04-22 · Naizhong Xu

Research Track A · General AI

Modern retrieval-augmented generation (RAG) systems treat vector embeddings as static, context-free artifacts: an embedding has no notion of when it was created, how trustworthy its source is, or which other embeddings depend on it. This flattening of knowledge has a measurable cost: recent work on VersionRAG reports t…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.3

MEMCoder: Multi-dimensional Evolving Memory for Private-Library-Oriented Code Generation

2026-04-27 · Mofei Li, Taozhi Chen, Guowei Yang, Jia Li

Research Track A · General AI

Large Language Models (LLMs) excel at general code generation, but their performance drops sharply in enterprise settings that rely on internal private libraries absent from public pre-training corpora. While Retrieval-Augmented Generation (RAG) offers a training-free alternative by providing static API documentation, …

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.3

Contextual Agentic Memory is a Memo, Not True Memory

2026-04-30 · Binyan Xu, Xilin Dai, Kehuan Zhang

Research Track A · General AI

Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they implement lookup. We argue that treating lookup as memory is a category error with provable consequences for agent capability, long-term learning, and security. Retrie…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

Non-Equilibrium Stochastic Dynamics as a Unified Framework for Insight and Repetitive Learning: A Kramers Escape Approach to Continual Learning

2026-04-05 · Gunn Kim

Research Track A · General AI

Continual learning in artificial neural networks is fundamentally limited by the stability--plasticity dilemma: systems that retain prior knowledge tend to resist acquiring new knowledge, and vice versa. Existing approaches, most notably elastic weight consolidation~(EWC), address this empirically without a physical ac…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutions

2026-04-07 · Manuel Barusco, Francesco Borsatti, David Petrovic, Davide Dalle Pezze, Gian Antonio Susto

Research Track A · General AI

Visual Anomaly Detection (VAD) is a critical task for many applications including industrial inspection and healthcare. While VAD has been extensively studied, two key challenges remain largely unaddressed in conjunction: edge deployment, where computational resources are severely constrained, and continual learning, w…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

ELC: Evidential Lifelong Classifier for Uncertainty Aware Radar Pulse Classification

2026-04-08 · Mohamed Rabie, Chinthana Panagamuwa, Konstantinos G. Kyriakopoulos

Research Track A

Reliable radar pulse classification is essential in Electromagnetic Warfare for situational awareness and decision support. Deep Neural Networks have shown strong performance in radar pulse and RF emitter recognition; however, on their own they struggle to efficiently learn new pulses and lack mechanisms for expressing…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers

2026-04-09 · Danit Yanowsky, Daphna Weinshall

Research Track A · General AI

Catastrophic forgetting remains a key challenge in Continual Learning (CL). In replay-based CL with severe memory constraints, performance critically depends on the sample selection strategy for the replay buffer. Most existing approaches construct memory buffers using embeddings learned under supervised objectives. Ho…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussion

2026-04-19 · Ou Wu

Research Track A · General AI

Large language model optimization has historically bifurcated into isolated data-centric and model-centric paradigms: the former manipulates involved samples through selection, augmentation, or poisoning, while the latter tunes model weights via masking, quantization, or low-rank adaptation. This paper establishes a un…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

Incremental learning for audio classification with Hebbian Deep Neural Networks

2026-04-20 · Riccardo Casciotti, Francesco De Santis, Alberto Antonietti, Annamaria Mesaros

Research Track A

The ability of humans for lifelong learning is an inspiration for deep learning methods and in particular for continual learning. In this work, we apply Hebbian learning, a biologically inspired learning process, to sound classification. We propose a kernel plasticity approach that selectively modulates network kernels…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery

2026-05-02 · Wenhao Li, Xiu Su, Yichao Cao, Hongyan Xu, Xiaobo Xia, Shan You, Yi Chen, Chang Xu

Research Track A · General AI

Vision-language-action (VLA) models have advanced the field of embodied manipulation by harnessing broad world knowledge and strong generalization. However, current VLA models still face several key challenges, including limited reasoning capability, lack of status monitoring, and difficulty in self-correction. In this…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

KAN-CL: Per-Knot Importance Regularization for Continual Learning with Kolmogorov-Arnold Networks

2026-05-12 · Minjong Cheon

Research Track A · General AI

Catastrophic forgetting remains the central obstacle in continual learning (CL): parameters shared across tasks interfere with one another, and existing regularization methods such as EWC and SI apply uniform penalties without awareness of which input region a parameter serves. We propose KAN-CL, a continual learning f…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging

2026-05-12 · Neha Verma, Nikhil Mehta, Shao-Chuan Wang, Naijing Zhang, Alicia Tsai, Li Wei, Lukasz Heldt, Lichan Hong, Ed Chi, Xinyang Yi

Research Track A · General AI

Despite the rapid advancements in large language model (LLM) development, fine-tuning them for specific tasks often results in the catastrophic forgetting of their general, language-based reasoning abilities. This work investigates and addresses this challenge in the context of the Generative Retrieval (GenRetrieval) t…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning

2026-05-20 · Kei Hiroshima, Kento Uchida, Shinichi Shirakawa

Research Track A · General AI

Continual learning (CL) aims to train models sequentially on multiple tasks while mitigating catastrophic forgetting of previously learned knowledge. Recent advances in large pre-trained models (LPMs) and model merging techniques, such as MAGMAX, have demonstrated effective CL performance by combining task-specific par…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

CLANE: Continual Learning of Actions on Neuromorphic Hardware from Event Cameras

2026-05-27 · Elvin Hajizada, Michael Neumeier, Edward Paxon Frady, Yulia Sandamirskaya, Axel von Arnim, Bing Li, Eyke Hüllermeier

Research Track A · General AI

Recognizing and continuously learning novel human actions without forgetting prior classes is a requirement for emerging AR/VR and robotics applications. For these applications, both on-device processing and learning are essential for privacy and low-latency adaptation. Event cameras address the efficiency of visual se…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies

2026-05-28 · Kajetan Schweighofer, Conor F. Hayes, Roberto Dailey, Risto Miikkulainen, Xin Qiu

Research Track A · General AI

Evolution Strategies (ES) has recently emerged as a competitive alternative to reinforcement learning (RL) for large language model (LLM) fine-tuning, offering advantages through simplicity, scalability, and inference-only training. However, recent work suggests that ES fine-tuning on new tasks may induce forgetting of…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.0

Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning

2026-06-09 · Bocheng Ju, Jianhua Wang, Chengliang Liu, Xiaolin Chang

Research Track A · General AI

Large language model unlearning aims to suppress designated undesirable knowledge while preserving benign capabilities. Many unlearning objectives focus on suppressing undesired answers, while recent target-guided variants specify replacement behavior but still leave update locality largely unconstrained. This paper in…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.9

Towards Continuous Power Forecasting: Practical Continual Learning for Real-World Energy Systems in Nonstationary Time Series

2026-06-23 · Yujiang He, Frederic Uhrweiller, Bernhard Sick

Research Track A

Power forecasting models deployed in real-world energy markets must operate under nonstationary conditions, where data distributions continually evolve due to weather variability, infrastructure upgrades, and changing consumption behaviors. In practice, these models face strict operational constraints: historical data …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.8

ASPIRE: Agentic /Skills Discovery for Robotics

2026-06-30 · Runyu Lu, Yubo Wu, Ethan Kou, Letian Fu, Wenli Xiao, Ajay Mandlekar, Yinzhen Xu, Guanya Shi, Ken Goldberg, Ang Chen, Mosharaf Chowdhury, Yuke Zhu, Linxi "Jim" Fan, Guanzhi Wang

Research Track A · General AI

Traditional robot programming is challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse configurations and execution failures. We introduce ASPIRE (Agentic Skill Programming through Iterative Robot Exploration), a continual learning system that autonomousl…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.6

Multi-Head Recurrent Memory Agents

2026-07-01 · Jiatong Li, Samuel Yeh, Sharon Li

Research Track A · General AI

Recurrent memory agents extend LLMs to arbitrarily long contexts by iteratively consolidating input into a fixed-size memory window. Despite their scalability, these agents exhibit a well-documented reliability problem: end-to-end performance degrades systematically as context length grows. We diagnose this failure by …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.5

On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models

2026-03-29 · Chongyang Zhao, Mingsong Li, Haodong Lu, Dong Gong

Research Track A · General AI

Multimodal Continual Instruction Tuning aims to continually enhance Large Vision Language Models (LVLMs) by learning from new data without forgetting previously acquired knowledge. Mixture of Experts (MoE) architectures naturally facilitate this by incrementally adding new experts and expanding routers while keeping th…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.5

Analytic Drift Resister for Non-Exemplar Continual Graph Learning

2026-04-03 · Lei Song, Shihan Guan, Youyong Kong

Research Track A · General AI

Non-Exemplar Continual Graph Learning (NECGL) seeks to eliminate the privacy risks intrinsic to rehearsal-based paradigms by retaining solely class-level prototype representations rather than raw graph examples for mitigating catastrophic forgetting. However, this design choice inevitably precipitates feature drift. As…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.5

Is Prompt Selection Necessary for Task-Free Online Continual Learning?

2026-04-06 · Seoyoung Park, Haemin Lee, Hankook Lee

Research Track A · General AI

Task-free online continual learning has recently emerged as a realistic paradigm for addressing continual learning in dynamic, real-world environments, where data arrive in a non-stationary stream without clear task boundaries and can only be observed once. To consider such challenging scenarios, many recent approaches…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.5

From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity

2026-04-09 · Zhuang Qi, Ying-Peng Tang, Lei Meng, Guoqing Chao, Lei Wu, Han Yu, Xiangxu Meng

Research Track A

Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representative samples from past tasks. Existing studies focus on designing sample-importance estimation mechanisms to identify information-rich samples. However, they typically ove…

Review
pending
Role
unreviewed
Read
now
huggingface Score 15.5

OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation

2026-06-16 · Guibin Zhang, Xun Xu, Yanwei Yue, Zikun Su, Wangchunshu Zhou, Xiaobin Hu, Shuicheng Yan

Research Track A · General AI

Memory has become a standard substrate for self-evolving agents, yet retaining experience is not the same as learning how to evolve through it. Existing memory agents can store trajectories, retrieve reflections, or accumulate skills, but often lack the holistic competence to select useful experience, act on it, write …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.3

Novel Memory Forgetting Techniques for Autonomous AI Agents: Balancing Relevance and Efficiency

2026-04-02 · Payal Fofadiya, Sunil Tiwari

Research Track A · General AI

Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation. Benchmarks such as LOCOMO and LOCCO report performance degradation from 0.455 to 0.05 across stages, while MultiWOZ shows 78.2% accuracy with 6.8% false …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.3

Memory as Metabolism: A Design for Companion Knowledge Systems

2026-04-13 · Stefan Miteski

Research Track A · General AI

Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory architectures emerged in April 2026 -- design proposals from Karpathy, MemPalace, and LLM Wiki v2 that compile knowledge into an interlinked artifact for long-term use by a …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.3

Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents

2026-04-22 · Yuxuan Cai, Jie Zhou, Qin Chen, Liang He, Wei Li, Xin Li, Bo Zhang

Research Track A · General AI

Online lifelong learning enables agents to accumulate experience across interactions and continually improve on long-horizon tasks. However, existing methods typically treat retrieval from past experience as a passive operation, triggering it only at task initialization or after completing a step. Consequently, agents …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.3

DYNA : Dynamic Episodic Memory Networks for Augmenting Large Language Models with Temporal Knowledge Graphs in Continuous Learning

2026-06-14 · Ali Sarabadani, Mahtab Tajvidiyan

Research Track A · General AI

Large Language Models (LLMs) struggle to incorporate new knowledge without forgetting or costly retraining. We propose DYNA, a lightweight framework that augments a frozen LLM with a temporal knowledge graph where events are nodes and temporal relations are directed, timestamped edges. The graph serves as an external, …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.0

Fast Spatial Memory with Elastic Test-Time Training

2026-04-08 · Ziqiao Ma, Xueyang Yu, Haoyu Zhen, Yuncong Yang, Joyce Chai, Chuang Gan

Research Track A · General AI

Large Chunk Test-Time Training (LaCT) has shown strong performance on long-context 3D reconstruction, but its fully plastic inference-time updates remain vulnerable to catastrophic forgetting and overfitting. As a result, LaCT is typically instantiated with a single large chunk spanning the full input sequence, falling…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.0

Tree Learning: A Multi-Skill Continual Learning Framework for Humanoid Robots

2026-04-14 · Yifei Yan, Linqi Ye

Research Track A · General AI

As reinforcement learning for humanoid robots evolves from single-task to multi-skill paradigms, efficiently expanding new skills while avoiding catastrophic forgetting has become a key challenge in embodied intelligence. Existing approaches either rely on complex topology adjustments in Mixture-of-Experts (MoE) models…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.0

SCM: Sleep-Consolidated Memory with Algorithmic Forgetting for Large Language Models

2026-04-22 · Saish Sachin Shinde

Research Track A · General AI

We present SCM (Sleep-Consolidated Memory), a research preview of a memory architecture for large language models that draws on neuroscientific principles to address a fundamental limitation in current systems: the absence of persistent, structured, and biologically plausible memory. Existing approaches rely on truncat…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.0

Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning

2026-06-04 · Ayushman Trivedi, Bhavika Melwani

Research Track A

Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning. In this work, we investigate an alternative perspective: that forgetting may arise not from complete destruction of task representations but from a loss of accessibility to preserved …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.0

Revisiting Prototype Rehearsal for Exemplar-Free Continual Learning: Manifold-Aware Boundary Sampling with Adaptive Class-Balanced Loss

2026-06-04 · Hongye Xu, Bartosz Krawczyk

Research Track A · General AI

Exemplar-free class-incremental learning (EFCIL) aims to acquire new classes over time without storing raw data. Historically, prototype rehearsal, which samples around stored class prototypes and mixes them with current-task data, has been a popular strategy to reduce catastrophic forgetting. However, recent drift-com…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.0

Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning

2026-06-04 · Hongye Xu, Bartosz Krawczyk

Research Track A · General AI

Continual learning (CL) seeks models that acquire new skills without erasing prior knowledge. In exemplar-free class-incremental learning (EFCIL), this challenge is amplified because past data cannot be stored, making representation drift for old classes particularly harmful. Prototype-based EFCIL is attractive for its…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.0

Continual Quadruped Robots Coordination via Semantic Skill Discovery

2026-06-06 · Daoqing Wang, Yuchen Xiao, Weixuan Huang, Zhilong Zhang, Shenghua Wan, Meng Li, Lei Yuan, Yang Yu

Research Track A · General AI

Multi-quadruped coordination has attracted increasing attention due to its enhanced payload capacity, broader contact coverage, and improved adaptability to challenging tasks. Existing methods for multi-quadruped manipulation typically focus on predefined or closed task families, often relying on multi-agent reinforcem…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.0

MOSAIC: Modality-Specific Adaptation for Incremental Continual Learning in Parkinson's Disease Gait Assessment

2026-06-11 · Minlin Zeng, Zhipeng Zhou, Yang Qiu, Martin J. McKeown, Zhiqi Shen

Research Track A · General AI

Gait-based Parkinson's disease assessment increasingly relies on heterogeneous sensors, but clinical systems rarely collect all modalities simultaneously. New sensors may arrive through device upgrades, protocol changes, or multi-center deployment, while historical patient data are often unavailable because of privacy …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.0

The Stable Recovery Manifold: Geometric Principles Governing Recoverability in Continual Learning

2026-06-11 · Ayushman Trivedi, Bhavika Melwani

Research Track A · General AI

Catastrophic forgetting is often viewed as the destruction of previously learned knowledge during sequential learning. Building on the Accessibility Collapse framework, we investigate the geometric structure of recoverability in continual learning. Using Split CIFAR-100 and a sequentially trained ResNet-18, we analyze …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.0

Understanding Cross-Modal Contributions in Continual Vision-Language Models: A Theoretical Perspective

2026-06-12 · Salimeh Sekeh, Mary Wisell

Research Track A · General AI

Continual vision-language models are commonly addressed through sequential fine-tuning; however, although this paradigm enables adaptation to new environments (tasks), it inherently emphasizes the contribution of previously learned environments (tasks) at the expense of the stability required to preserve previously acq…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.0

Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation

2026-06-29 · Naeem Paeedeh, Mahardhika Pratama, Wolfgang Mayer, Mukesh Prasad, Weiping Ding, Yew-Soon Ong

Research Track A · General AI

Existing domain-incremental learning (DIL) strategies call for massive amounts of data to adapt to new domains and suffer from the overfitting problem in the case of data scarcity. This paper puts forward a relatively uncharted problem, namely, few-shot domain incremental learning (FSDIL), taking into account the probl…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.8

ISM:Self-Improving Strategy Memory for Continual Mathematical Reasoning

2026-06-30 · Prakhar Dixit, Tim Oates

Research Track A · General AI

We propose Intelligent Schema Memory (ISM), a self-evolving memory-augmented system that improves mathematical reasoning for a frozen LLM under continual learning with hard episodic resets. ISM maintains a compact, self-refined bank of strategy schemas learned from both successful and failed episodes, with symbolic too…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.5

Lifelong Embodied Navigation Learning

2026-03-06 · Xudong Wang, Jiahua Dong, Baichen Liu, Qi Lyu, Lianqing Liu, Zhi Han

Research Track A · General AI

Embodied navigation agents powered by large language models have shown strong performance on individual tasks but struggle to continually acquire new navigation skills, which suffer from catastrophic forgetting. We formalize this challenge as lifelong embodied navigation learning (LENL), where an agent is required to a…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.5

Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces

2026-03-15 · Jiayuan Du, Yuebing Song, Yiming Zhao, Xianghui Pan, Jiawei Lian, Yuchu Lu, Liuyi Wang, Chengju Liu, Qijun Chen

Research Track A · General AI

End-to-End autonomous driving (E2E-AD) systems face challenges in lifelong learning, including catastrophic forgetting, difficulty in knowledge transfer across diverse scenarios, and spurious correlations between unobservable confounders and true driving intents. To address these issues, we propose DeLL, a Deconfounded…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.5

ReConText3D: Replay-based Continual Text-to-3D Generation

2026-04-15 · Muhammad Ahmed Ullah Khan, Muhammad Haris Bin Amir, Didier Stricker, Muhammad Zeshan Afzal

Research Track A · General AI

Continual learning enables models to acquire new knowledge over time while retaining previously learned capabilities. However, its application to text-to-3D generation remains unexplored. We present ReConText3D, the first framework for continual text-to-3D generation. We first demonstrate that existing text-to-3D model…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.5

Sequential Learning and Catastrophic Forgetting in Differentiable Resistor Networks

2026-05-02 · Maniru Ibrahim

Research Track A

Differentiable physical networks provide a simple setting in which learning can be studied through the interaction between trainable parameters and physical equilibrium constraints. We investigate sequential learning in differentiable resistor networks governed by Kirchhoff's laws. Although individual input--output map…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.5

Unlocking Compositional Generalization in Continual Few-Shot Learning

2026-05-12 · Phu-Quy Nguyen-Lam, Phu-Hoa Pham, Dao Sy Duy Minh, Chi-Nguyen Tran, Huynh Trung Kiet, Long Tran-Thanh

Research Track A · General AI

Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it into individual object-level parts that can be matched and compared across different concepts. In practice, this potential is rarely realized. Continual learners either co…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.4

Black-Box Continual Learning for Vision-Language Models

2026-06-22 · Yuting Li, Weihang Fang, Haoyuan Gao, Linghe Kong, Yexin Li, Lichao Sun, Weiran Huang

Research Track A · General AI

The rapid deployment of Vision-Language Models (VLMs) in dynamic environments necessitates the ability to learn continuously without forgetting. However, traditional continual learning (CL) settings often rely on white-box paradigms, which is increasingly invalidated by the shift toward cloud-hosted models. In this pap…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.3

ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents

2026-04-15 · Zhuofeng Li, Yi Lu, Dongfu Jiang, Haoxiang Zhang, Yuyang Bai, Chuan Li, Yu Wang, Shuiwang Ji, Jianwen Xie, Yu Zhang

Research Track A · General AI

The rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support. However, LLM-based reviewers often generate superficial, formulaic comments lacking substantive, evidence-grounded feedback. We attribute this to the underutilization of two key compone…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.3

CoRE: Concept-Reasoning Expansion for Continual Brain Lesion Segmentation

2026-04-28 · Qianqian Chen, Anglin Liu, Jingyang Zhang, Yudong Zhang

Research Track A · General AI

Accurate brain lesion segmentation in MRI is vital for effective clinical diagnosis and treatment planning. Due to high annotation costs and strict data privacy regulations, universal models require employing Continual Learning (CL) to adapt to evolving clinical tasks without losing previously acquired knowledge. Howev…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models

2026-03-22 · Elif Ceren Gok Yildirim, Murat Onur Yildirim, Joaquin Vanschoren

Research Track A · General AI

The continual learning literature has rapidly shifted from traditional class incremental learning (CIL) techniques to foundation model (FM)-based CIL methods without a clear understanding of how these newer approaches compare to strong, lightweight convolutional baselines. This abrupt transition has created a substanti…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

Chameleons do not Forget: Prompt-Based Online Continual Learning for Next Activity Prediction

2026-04-01 · Marwan Hassani, Tamara Verbeek, Sjoerd van Straten

Research Track A

Predictive process monitoring (PPM) focuses on predicting future process trajectories, including next activity predictions. This is crucial in dynamic environments where processes change or face uncertainty. However, current frameworks often assume a static environment, overlooking dynamic characteristics and concept d…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

2026-04-02 · Xinlei Yu, Zhangquan Chen, Yongbo He, Tianyu Fu, Cheng Yang, Chengming Xu, Yue Ma, Xiaobin Hu, Zhe Cao, Jie Xu, Guibin Zhang, Jiale Tao, Jiayi Zhang, Siyuan Ma, Kaituo Feng, Haojie Huang, Youxing Li, Ronghao Chen, Huacan Wang, Chenglin Wu, Zikun Su, Xiaogang Xu, Kelu Yao, Kun Wang, Chen Gao, Yue Liao, Ruqi Huang, Tao Jin, Cheng Tan, Jiangning Zhang, Wenqi Ren, Yanwei Fu, Yong Liu, Yu Wang, Xiangyu Yue, Yu-Gang Jiang, Shuicheng Yan

Research Track A · General AI

Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an increasing body of work shows that many critical internal processes are more naturally carried out in continuous latent space than in human-rea…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs

2026-04-03 · Linyu Li, Zhi Jin, Yichi Zhang, Dongming Jin, Yuanpeng He, Haoran Duan, Gadeng Luosang, Nyima Tashi

Research Track A · General AI

Real-world multimodal knowledge graphs (MMKGs) are dynamic, with new entities, relations, and multimodal knowledge emerging over time. Existing continual knowledge graph reasoning (CKGR) methods focus on structural triples and cannot fully exploit multimodal signals from new entities. Existing multimodal knowledge grap…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

A Faster Path to Continual Learning

2026-04-13 · Wei Li, Hangjie Yuan, Zixiang Zhao, Borui Kang, Ziwei Liu, Tao Feng

Research Track A

Continual Learning (CL) aims to train neural networks on a dynamic stream of tasks without forgetting previously learned knowledge. Among optimization-based approaches, C-Flat has emerged as a promising solution due to its plug-and-play nature and its ability to encourage uniformly low-loss regions for both new and old…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replay

2026-04-15 · Qianyu Chen, Shujian Yu

Research Track A

Functional magnetic resonance imaging (fMRI) is widely used for studying and diagnosing brain disorders, with functional connectivity (FC) matrices providing powerful representations of large-scale neural interactions. However, existing diagnostic models are trained either on a single site or under full multi-site acce…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

AIM: Asymmetric Information Masking for Visual Question Answering Continual Learning

2026-04-16 · Peifeng Zhang, Zice Qiu, Donghua Yu, Shilei Cao, Juepeng Zheng, Yutong Lu, Haohuan Fu

Research Track A · General AI

In continual visual question answering (VQA), existing Continual Learning (CL) methods are mostly built for symmetric, unimodal architectures. However, modern Vision-Language Models (VLMs) violate this assumption, as their trainable components are inherently asymmetric. This structural mismatch renders VLMs highly pron…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning

2026-04-16 · Amirhosein Javadi, Tuomas Oikarinen, Tara Javidi, Tsui-Wei Weng

Research Track A · General AI

Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a new task. This issue is especially pronounced in class incremental learning (CIL), which is the most challenging setting in continual learning. Existing methods to address …

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

Tree of Concepts: Interpretable Continual Learners in Non-Stationary Clinical Domains

2026-04-18 · Dongkyu Cho, Xiyue Li, Samrachana Adhikari, Rumi Chunara

Research Track A · General AI

Continual learning aims to update models under distribution shift without forgetting, yet many high-stakes deployments, such as healthcare, also require interpretability. In practice, models that adapt well (e.g., deep networks) are often opaque, while models that are interpretable (e.g., decision trees) are brittle un…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems

2026-04-22 · Beining Wu, Jun Huang

Research Track A

Federated continual learning (FCL) allows distributed autonomous fleets to adapt collaboratively to evolving terrain types across extended mission lifecycles. However, current approaches face several key challenges: 1) they use uniform protection strategies that do not account for the varying sensitivities to forgettin…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

Temporally Extended Mixture-of-Experts Models

2026-04-22 · Zeyu Shen, Peter Henderson

Research Track A · General AI

Mixture-of-Experts models, now popular for scaling capacity at fixed inference speed, switch experts at nearly every token. Once a model outgrows available GPU memory, this churn can render optimizations like offloading and pre-fetching ineffective. We make the case that the options framework in reinforcement learning …

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

Fine-Tuning Regimes Define Distinct Continual Learning Problems

2026-04-23 · Paul-Tiberiu Iordache, Elena Burceanu

Research Track A · General AI

Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite substantial progress in benchmarking CL methods, comparative evaluations typically keep the fine-tuning regime fixed. In this paper, we argue that the fine-tuning regime, defined by the trainable …

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

Leveraging LLMs for Multi-File DSL Code Generation: An Industrial Case Study

2026-04-27 · Sivajeet Chand, Kevin Nguyen, Peter Kuntz, Alexander Pretschner

Research Track A · General AI

Large language models (LLMs) perform strongly on general-purpose code generation, yet their applicability to enterprise domain-specific languages (DSLs) remains underexplored, especially for repository-scale change generation spanning multiple files and folder structures from a single natural-language (NL) instruction.…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

Learning to Forget: Continual Learning with Adaptive Weight Decay

2026-04-29 · Aditya A. Ramesh, Alex Lewandowski, Jürgen Schmidhuber

Research Track A · General AI

Continual learning agents with finite capacity must balance acquiring new knowledge with retaining the old. This requires controlled forgetting of knowledge that is no longer needed, freeing up capacity to learn. Weight decay, viewed as a mechanism for forgetting, can serve this role by gradually discarding information…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

Manufactured Confidence: How Memory Consolidation Turns Hearsay into Confident Facts

2026-06-28 · Alex Kwon

Research Track A · General AI

LLM agents carry conclusions across steps and sessions in compressed memory, and memory products (e.g., mem0, LangMem) rewrite conversation into stored "facts" that later steps trust. We show this rewriting manufactures confidence: across our constructed agent settings, a casual, hedged remark becomes a confident, date…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.8

OptArgus: A Multi-Agent System to Detect Hallucinations in LLM-based Optimization Modeling

2026-05-12 · Zhong Li, Zihan Guo, Xiaohan Lu, Juntao Wang, Jie Song, Chao Shen, Jiageng Wu, Mingyang Sun

Research Track A · General AI

Large language models (LLMs) are increasingly used to translate natural-language optimization problems into mathematical formulations and solver code, but matching the reference objective value is not a reliable test of correctness: an artifact may agree numerically while still changing the underlying optimization sema…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.8

Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments

2026-05-27 · Julia Hindel, Simon Bultmann, Houman Masnavi, Daniele Cattaneo, Abhinav Valada

Research Track A · General AI

Self-supervised online traversability estimation enables robots to continuously learn from unlabeled open-world experiences and adapt their navigation behavior toward safe and efficient trajectories. Existing approaches either rely on handcrafted proprioceptive traversability scores, limiting robot-agnosticism, or clus…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.8

Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving

2026-06-29 · Cheng Gong, Haoyang Wang, Chao Lu, Zirui Li, Jianwei Gong

Research Track A · General AI

Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations. However, most learning-based policies are trained or fine-tuned on expert demonstrations and then rely largely on generalization to handle challenging closed-loop scenar…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.5

Dual-Imbalance Continual Learning for Real-World Food Recognition

2026-03-31 · Xiaoyan Zhang, Jiangpeng He

Research Track A · General AI

Visual food recognition in real-world dietary logging scenarios naturally exhibits severe data imbalance, where a small number of food categories appear frequently while many others occur rarely, resulting in long-tailed class distributions. In practice, food recognition systems often operate in a continual learning se…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.5

Phase model analysis of the effect of M-current on neural synchrony in hippocampal networks

2026-06-10 · Megha Manoj, Sue Ann Campbell

Research Track A

Neural assemblies, transiently coordinated groups of neurons, observed in the hippocampus are thought to underlie the formation of episodic memories. Acetylcholine (ACh), a neuromodulator, that is received by the hippocampus, plays a critical role in memory and learning. A well supported hypothesis suggests that high l…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.5

CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning

2026-06-30 · Julien Lefebvre, Stefan Duffner, Mathieu Lefort

Research Track A · General AI

Online Continual Self-Supervised Learning (OCSSL) aims to learn representations from a continuous stream of unlabeled data, without knowledge of task boundaries and under memory constraints. Existing methods rely either on replay buffers that exploit latent space structure, or on regularization alone. We present CLIMB …

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems

2026-03-27 · Shanglin Wu, Yuyang Luo, Yueqing Liang, Kaiwen Shi, Yanfang Ye, Ali Payani, Kai Shu

Research Track A · General AI

Large language model (LLM) multi-agent systems can scale along two distinct dimensions: by increasing the number of agents and by improving through accumulated experience over time. Although prior work has studied these dimensions separately, their interaction under realistic cost constraints remains unclear. In this p…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

RL-Driven Sustainable Land-Use Allocation for the Lake Malawi Basin

2026-04-04 · Ying Yao

Research Track A · General AI

Unsustainable land-use practices in ecologically sensitive regions threaten biodiversity, water resources, and the livelihoods of millions. This paper presents a deep reinforcement learning (RL) framework for optimizing land-use allocation in the Lake Malawi Basin to maximize total ecosystem service value (ESV). Drawin…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic Agent

2026-04-08 · Bingxuan Li, Simo Du, Yue Guo

Research Track A · General AI

Clinical expertise improves not only by acquiring medical knowledge, but by accumulating experience that yields reusable diagnostic patterns. Recent LLMs-based diagnostic agents have shown promising progress in clinical reasoning for decision support. However, most approaches treat cases independently, limiting experie…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning

2026-04-09 · Shiwan Zhao, Zhihu Wang, Xuyang Zhao, Jiaming Zhou, Caiyue Xu, Chenfei Liu, Liting Zhang, Yuhang Jia, Yanzhe Zhang, Hualong Yu, Zichen Xu, Qicheng Li, Yong Qin

Research Track A · General AI

Post-training has become central to turning pretrained large language models (LLMs) into aligned and deployable systems. Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL), process supervision, verifier-guided methods, distillation, and multi-stage pipelines. Yet th…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

StructMem: Structured Memory for Long-Horizon Behavior in LLMs

2026-04-23 · Buqiang Xu, Yijun Chen, Jizhan Fang, Ruobin Zhong, Yunzhi Yao, Yuqi Zhu, Lun Du, Shumin Deng

Research Track A · General AI

Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat memory is efficient but fails to model relational structure, while graph-based m…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

MARD: A Multi-Agent Framework for Robust Android Malware Detection

2026-04-28 · Xueying Zeng, Youquan Xian, Sihao Liu, Xudong Mou, Yanze Li, Lei Cui, Bo Li

Research Track A · General AI

With the rapid evolution of Android applications, traditional machine learning-based detection models suffer from concept drift. Additionally, they are constrained by shallow features, lacking deep semantic understanding and interpretability of decisions. Although Large Language Models (LLMs) demonstrate remarkable sem…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

2026-06-03 · Jingwen Chen, Wenkai Yang, Shengda Fan, Wenbo Nie, Chenxing Sun, Shaodong Zheng, Yangen Hu, Lu Pan, Ke Zeng, Yankai Lin

Research Track A · General AI

Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large language models (LLMs). While prior work has predominantly focused on single-iteration transfer, we discover that under multi-iteration exper…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

LargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models

2026-06-08 · Mingqi Yuan, Xiaoquan Sun, Shihao Luo, Jiayu Chen

Research Track A · General AI

Online task-free continual learning (TFCL) requires intelligent agents to sequentially accumulate knowledge from an unbounded, non-stationary data stream under strict single-pass constraints and without any explicit task identifiers. Existing online TFCL paradigms primarily rely on parameter-efficient prompt tuning or …

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

Episodic-to-Semantic Consolidation Without Identity Drift

2026-07-02 · Xue Qin, Simin Luan, Cong Yang, Zhijun Li

Research Track A · General AI

Long-running adaptive intelligent agents face a structural tension between knowledge consolidation and information integrity. Memory consolidation is conventionally treated as an agent-changing operation: a model is fine-tuned, a prompt rewritten, a policy distilled, or a reflection appended to the context that governs…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.0

Learning from Many and Adapting to the Unknown in Open-set Test Streams

2026-04-01 · Xiao Zhang, Juntao Lyu, Tianyu Hu, Qianchuan Zhao, Huimin Ma

Research Track A · General AI

Large Language Models (LLMs) generalize across tasks via reusable representations and flexible reasoning, yet remain brittle in real deployment under evolving tasks and continual distribution shift. A common approach is Test-Time Adaptation (TTA), existing ones of which updates models with hand-designed unsupervised ob…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.0

CobwebTM: Probabilistic Concept Formation for Lifelong and Hierarchical Topic Modeling

2026-04-15 · Karthik Singaravadivelan, Anant Gupta, Zekun Wang, Christopher MacLellan, Christopher J. MacLellan

Research Track A

Topic modeling seeks to uncover latent semantic structure in text corpora with minimal supervision. Neural approaches achieve strong performance but require extensive tuning and struggle with lifelong learning due to catastrophic forgetting and fixed capacity, while classical probabilistic models lack flexibility and a…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.0

AEGIS: Anchor-Enforced Gradient Isolation for Knowledge-Preserving Vision-Language-Action Fine-Tuning

2026-04-17 · Guransh Singh

Research Track A

Adapting pre-trained vision-language models (VLMs) for robotic control requires injecting high-magnitude continuous gradients from a flow-matching action expert into a backbone trained exclusively with cross-entropy. This cross-modal gradient asymmetry - the spectral dimensionality mismatch between low-rank MSE regress…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.0

Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigation

2026-04-23 · Yi-Ling Liu, Melvin Laux, Mariela De Lucas Alvarez, Frank Kirchner, Rebecca Adam

Research Track A · General AI

Autonomous underwater vehicles are required to perform multiple tasks adaptively and in an explainable manner under dynamic, uncertain conditions and limited sensing, challenges that classical controllers struggle to address. This demands robust, generalizable, and inherently interpretable control policies for reliable…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.0

Automated In-the-Wild Data Collection for Continual AI Generated Image Detection

2026-05-04 · Thanasis Pantsios, Dimitrios Karageorgiou, Christos Koutlis, George Karantaidis, Olga Papadopoulou, Symeon Papadopoulos

Research Track A · General AI

The rapid advancement of generative Artificial Intelligence (AI) has introduced significant challenges for reliable AI-generated image detection. Existing detectors often suffer from performance degradation under distribution shifts and when encountering newly emerging generative models. In this work, we propose a data…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.0

Convergence of Continual Learning in Homogeneous Deep Networks

2026-06-29 · Matan Schliserman, Gon Buzaglo, Itay Evron, Daniel Soudry

Research Track A

We characterize weakly regularized continual classification in homogeneous models as sequential projections onto task margin sets. This result generalizes prior analyses restricted to either stationary (single-task) deep models or continual linear models. We show that global convergence generally fails, even for simple…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.8

Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents

2026-05-20 · Chongrui Ye, Yuxiang Liu, Yu Wang, Haofei Yu, Yining Zhao, Ge Liu, Julian McAuley, Jiaxuan You

Research Track A · Research Track B · General AI

Language agents increasingly operate over streams of related tasks, yet existing memory systems struggle to convert accumulated experience into reusable knowledge. Retrieval-augmented and structured memory methods record per-session observations effectively, but often couple acquisition and consolidation into a single …

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.8

Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven Reasoning

2026-05-29 · Navin Sriram Ravie, Andrew Jong, Krrish Jain, John Liu, Omar Alama, Bijo Sebastian, Sebastian Scherer

Research Track A · General AI

In robotics, dangers and adversity modes are often embodiment-specific and relative to each agent. A frontier of autonomous mobile robotics is to enable agents to operate effectively in the wild in unseen unstructured environments. A significant challenge in unseen unstructured environments is that it may not be possib…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.8

EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision

2026-05-29 · Rosario Forte, Giuseppe Lando, Antonino Furnari

Research Track A · General AI

Continuous episodic memory is a core capability for autonomous agents operating in dynamic, real-world environments, yet current streaming video benchmarks provide limited tools for diagnosing what models remember and for how long. We introduce \egostream, a diagnostic benchmark for streaming episodic memory evaluation…

Review
pending
Role
unreviewed
Read
now
huggingface Score 12.8

AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models

2026-07-02 · Rintaro Otsubo, Ryo Fujii, Reina Ishikawa, Taiki Kanaya, Kanta Sawafuji, Hiroki Kajita, Shigeki Sakai, Hideo Saito, Ryo Hachiuma

Research Track A · General AI

Vision-Language Models (VLMs) have demonstrated immense promise in Spatio-Temporal Video Grounding (STVG). However, current evaluation protocols are largely confined to zero-shot assessments on general, daily-life benchmarks. This creates a critical disconnect from real-world applications in specialized fields, where m…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.5

Reframing Long-Tailed Learning via Loss Landscape Geometry

2026-03-22 · Shenghan Chen, Yiming Liu, Yanzhen Wang, Yujia Wang, Xiankai Lu

Research Track A · General AI

Balancing performance trade-off on long-tail (LT) data distributions remains a long-standing challenge. In this paper, we posit that this dilemma stems from a phenomenon called "tail performance degradation" (the model tends to severely overfit on head classes while quickly forgetting tail classes) and pose a solution …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 12.5

Continual Vision-Language Learning for Remote Sensing: Benchmarking and Analysis

2026-04-01 · Xingxing Weng, Ruifeng Ni, Chao Pang, XiangYu Hao, Yishan Wang, Xiaokang Zhang, Wei Xu, Gui-Song Xia

Research Track A · General AI

Current remote sensing vision-language models (RS VLMs) demonstrate impressive performance in image interpretation but rely on static training data, limiting their ability to accommodate continuously emerging sensing modalities and downstream tasks. This exposes a fundamental challenge: enabling RS VLMs to continually …

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.5

ProTPS: Prototype-Guided Text Prompt Selection for Continual Learning

2026-04-01 · Jie Mei, Li-Leng Peng, Keith Fuller, Jenq-Neng Hwang

Research Track A

For continual learning, text-prompt-based methods leverage text encoders and learnable prompts to encode semantic features for sequentially arrived classes over time. A common challenge encountered by existing works is how to learn unique text prompts, which implicitly carry semantic information of new classes, so that…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.5

Continual Hand-Eye Calibration for Open-world Robotic Manipulation

2026-04-17 · Fazeng Li, Gan Sun, Chenxi Liu, Yao He, Wei Cong, Yang Cong

Research Track A

Hand-eye calibration through visual localization is a critical capability for robotic manipulation in open-world environments. However, most deep learning-based calibration models suffer from catastrophic forgetting when adapting into unseen data amongst open-world scene changes, while simple rehearsal-based continual …

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.5

HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning

2026-04-17 · Eunju Lee, MiHyeon Kim, JuneHyoung Kwon, Yoonji Lee, JiHyun Kim, Soojin Jang, YoungBin Kim

Research Track A · General AI

Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) methods assume homogeneous domains and balanced data distributions, limiting real-world applicability where data arises from heterogeneous disciplines with imbalanced sample av…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.5

Anytime Training with Schedule-Free Spectral Optimization

2026-05-21 · Anuj Apte, Pranav Deshpande, Niraj Kumar, Shouvanik Chakrabarti, Junhyung Lyle Kim

Research Track A

Standard neural network training relies on learning-rate schedules tied to a fixed horizon, leading to strong path dependence and costly re-tuning as data availability changes. Schedule-Free (SF) methods address this by removing explicit schedules, yet SF-AdamW, the current state-of-the-art anytime optimizer, consisten…

Review
pending
Role
unreviewed
Read
now
huggingface Score 12.5

Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation

2026-06-04 · Hanxu Hu, Zdeněk Šnajdr, Pinzhen Chen, Jannis Vamvas, Rico Sennrich

Research Track A · General AI

Prior work has shown that large language models (LLMs) can translate unseen or low-resource languages by undergoing continued training or even by encoding a grammar book in their context. However, both methods typically overfit specific languages, with limited zero-shot transfer at test time. To translate extremely low…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.5

GUI-AC: Enhancing Continual Learning in GUI Agents

2026-06-09 · Can Lin, Tao Feng, Hangjie Yuan, Dan Zhang, Yifan Zhu, Zhonghong Ou

Research Track A · Research Track B · General AI

Graphical User Interfaces (GUIs) serve as the dominant medium for human-computer interaction, yet building GUI agents that generalize across the vast diversity of real-world interface environments, with the same flexibility and robustness that humans naturally exhibit, remains unsolved. Notably, GUI data are inherently…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.4

Fast and Slow Variational Continual Learning

2026-06-22 · Subarnaduti Paul, Yohan Jung, Mohammad Emtiyaz Khan, Siddharth Swaroop, Thomas Möllenhoff, Martin Mundt

Research Track A · General AI

Continual learning remains a major challenge for modern deep networks, partly because commonly used optimizers lack inherent mechanisms for continual adaptation. One such natural mechanism is fast and slow adaptation to balance stability and plasticity. This mechanism has deep roots in neuroscience and biology, but the…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.4

GCT-MARL: Graph-Based Contrastive Transfer for Sample-Efficient Cooperative Multi-Agent Reinforcement Learning

2026-06-23 · Animesh Animesh, Satheesh K Perepu, Kaushik Dey

Research Track A · General AI

In cooperative multi-agent reinforcement learning (MARL), from a deployment perspective, it is challenging and expensive to train agents from scratch for each new environment or task. In this work, we propose GCT-MARL, a transfer learning framework that builds on the multi-view graph contrastive backbone of MAIL and au…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.3

PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor

2026-04-01 · Yutao Yang, Junsong Li, Qianjun Pan, Jie Zhou, Kai Chen, Qin Chen, Jingyuan Zhao, Ningning Zhou, Xin Li, Liang He

Research Track A · General AI

Existing methods for AI psychological counselors predominantly rely on supervised fine-tuning using static dialogue datasets. However, this contrasts with human experts, who continuously refine their proficiency through clinical practice and accumulated experience. To bridge this gap, we propose an Experience-Driven Li…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.3

Lightweight LLM Agent Memory with Small Language Models

2026-04-09 · Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang, Pengcheng Zheng, Zhicheng Wang, Ping Guo, Fan Mo, Sung-Ho Bae, Jie Zou, Jiwei Wei, Yang Yang

Research Track A · General AI

Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memory systems incur low online overhead but suffer from unstable accuracy due to limited query construc…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.3

CASK: Core-Aware Selective KV Compression for Reasoning Traces

2026-04-13 · Buseong Kim, Heejun Gwon

Research Track A · General AI

In large language models performing long-form reasoning, the KV cache grows rapidly with decode length, creating bottlenecks in memory and inference stability. Existing reasoning-oriented KV compression has mostly followed an eviction-centered view: estimate token importance more accurately, then discard lower-ranked e…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.3

SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport

2026-07-01 · Yuting Zhang, Yanbei Liu, Zhitao Xiao, Lei Geng, Yanwei Pang, Xiao Wang

Research Track A · General AI

Self-supervised Continual Graph Learning (CGL) aims to successively learn from a graph sequence with different tasks without label supervision - a paradigm that has attracted widespread attention. Most existing self-supervised CGL methods rely on instance-level consistency objectives that enforce stability of individua…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.2

How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations

2026-06-24 · Yuxing Cheng, Yuan Wu, Yi Chang

Research Track A · General AI

Vision-language models (VLMs) have achieved strong performance on OCR-based benchmarks and increasingly focused on text-rich understanding, but their robustness under controlled visual degradation remains insufficiently understood. This gap is critical for OCR reasoning, where visual corruption can induce OCR errors an…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.0

LACE: Loss-Adaptive Capacity Expansion for Continual Learning

2026-03-30 · Shivnath Tathe

Research Track A

Fixed representational capacity is a fundamental constraint in continual learning: practitioners must guess an appropriate model width before training, without knowing how many distinct concepts the data contains. We propose LACE (Loss-Adaptive Capacity Expansion), a simple online mechanism that expands a model's repre…

Review
pending
Role
unreviewed
Read
now
huggingface Score 12.0

Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning

2026-04-01 · Mohammad R. Abu Ayyash

Research Track A · General AI

We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference. Five interlocking components: (1) MoE-LoRA with Shazeer-style noisy top-2 routing across all s…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.0

Adaptive Data Dropout: Towards Self-Regulated Learning in Deep Neural Networks

2026-04-14 · Amar Gahir, Varshil Patel, Shreyank N Gowda

Research Track A · General AI

Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equally throughout learning. Recent work shows that progressively reducing the amount of training data can improve efficiency and generalization, but existing methods rely on f…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.0

Why Fine-Tuning Encourages Hallucinations and How to Fix It

2026-04-16 · Guy Kaplan, Zorik Gekhman, Zhen Zhu, Lotem Rozner, Yuval Reif, Swabha Swayamdipta, Derek Hoiem, Roy Schwartz

Research Track A · General AI

Large language models are prone to hallucinating factually incorrect statements. A key source of these errors is exposure to new factual information through supervised fine-tuning (SFT), which can increase hallucinations w.r.t. knowledge acquired during pre-training. In this work, we explore whether SFT-induced halluci…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.0

Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less

2026-05-07 · Yuxing Liu, Jianyu Wang, Tong Zhang

Research Track A · General AI

Optimizers play an important role in both pretraining and finetuning stages when training large language models (LLMs). In this paper, we present an observation that full finetuning with the same optimizer as in pretraining achieves a better learning-forgetting tradeoff, i.e., forgetting less while achieving the same o…

Review
pending
Role
unreviewed
Read
now
huggingface Score 12.0

BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling

2026-06-08 · Gianluca Barmina, Annemette Broch Pirchert, Andrea Blasi Núñez, Lukas Galke Poech, Peter Schneider-Kamp

Research Track A · General AI

As deep learning models scale, managing, inspecting, and modifying large checkpoints has become increasingly challenging. Researchers often need to alter model weights for layer restructuring, precision casting, low-rank factorization, and architectural debugging, yet these workflows often rely on fragile ad-hoc Python…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.0

Accurate and Resource-Efficient Federated Continual Learning

2026-06-09 · Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan, Rajgopal Kannan, Viktor Prasanna

Research Track A · General AI

Federated continual learning (FCL) must learn from distributed task streams under limited resources, such as communication, computation, memory, and label availability. Existing FCL methods often rely on repeated local optimization, replay, and full supervision. Analytic alternatives avoid iterative training and replay…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.0

GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning

2026-06-12 · Mary Isabelle Wisell, Nicholas Jacobs, Aayush Manandhar, Salimeh Yasaei Sekeh

Research Track A · General AI

Multi-source transfer learning faces a fundamental scalability bottleneck: existing approaches require either loading all K source models into memory simultaneously during parameter fusion, requiring O(K) memory, or deploying all models at inference time, making production deployment infeasible. We propose GRASP (Gradi…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.8

SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions

2026-06-29 · Mohit Raghavendra, Anisha Gunjal, Aakash Sabharwal, Yunzhong He

Research Track A · General AI

We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks. Existing frontier SWE benchmarks typically provide complete requirements upfront and evaluate agents on autonomous implementation. In contrast, SWE-Interact places agents in a realis…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.5

COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game

2026-03-30 · Alkis Sygkounas, Rishi Hazra, Andreas Persson, Pedro Zuidberg Dos Martires, Amy Loutfi

Research Track A · General AI

A central challenge in building continually improving agents is that training environments are typically static or manually constructed. This restricts continual learning and generalization beyond the training distribution. We address this with COvolve, a co-evolutionary framework that leverages large language models (…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.5

MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound

2026-05-12 · Phu-Hoa Pham, Chi-Nguyen Tran, Nguyen Lam Phu Quy, Dao Sy Duy Minh, Huynh Trung Kiet, Long Tran-Thanh

Research Track A · General AI

Streaming decision trees are natural candidates for open-world continual learning, as they perform local updates, enjoy bounded memory, and static decision boundaries. Despite these, they still fail in online class-incremental learning due to two coupled miscalibrations: (i) their split criterion grows unreliable as th…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.5

HydraCIL: Decoupled Class-Incremental Learning through Prototype-Guided Multi-Head Classifiers

2026-06-08 · Daniel Vila-Cruz, Laura Morán-Fernández, Verónica Bolón-Canedo

Research Track A

We present HydraCIL, a decoupled continual learning model based on prototype-guided multi-head classifiers, targeting sustainable deployment in embedded and resource-constrained environments. While most Class-Incremental Learning (CIL) methods rely on powerful hardware and long retraining cycles, real-world systems, su…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.5

Preserving Plasticity in Continual Learning via Dynamical Isometry

2026-06-08 · Andries Rosseau, Robert Müller, Ann Nowé

Research Track A · General AI

Continual training of deep neural networks under non-stationarity often leads to a progressive loss of plasticity, eventually limiting further learning. We relate plasticity to the empirical Neural Tangent Kernel, and identify dynamical isometry (the condition that layer-wise Jacobian singular values remain close to on…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.5

Dimensionality Controls When Modularity Helps in Continual Learning

2026-06-16 · Kathrin Korte, Christian Medeiros Adriano, Joachim Winther Pedersen, Eleni Nisioti, Sebastian Risi

Research Track A

Compositional learning systems must balance plasticity, the ability to acquire new knowledge, with stability, the preservation of previously learned components, especially when tasks share structure and risk interference. We study how modular architecture, task similarity, and representational dimensionality jointly sh…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.5

DOPD: Dual On-policy Distillation

2026-06-29 · Xinlei Yu, Gen Li, Qingyi Si, Guibin Zhang, Yuqi Xu, Congcong Wang, Shuai Dong, Kaiwen Tuo, Xiangyu Zeng, Kaituo Feng, Qunzhong Wang, Yang Shi, Xiaobin Hu, Xiangyu Yue, Jiaqi Wang, Shuicheng Yan

Research Track A · General AI

On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals. To furnish high-quality supervision sources and thereby elevate the performance frontier of distillation, an intuitive direction is to infuse privileged information to either teache…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.5

Theory of Continual Learning Against Data Poisoning Attacks

2026-06-29 · Yiting Hu, Lingjie Duan

Research Track A · General AI

Continual learning (CL), where a model is trained on a sequence of data tasks, is increasingly being adopted across key fields such as large language models and image recognition, yet it remains highly vulnerable to data poisoning that triggers learning divergence or severe excess risk. Despite these threats, a princip…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.3

SOMA: Strategic Orchestration and Memory-Augmented System for Vision-Language-Action Model Robustness via In-Context Adaptation

2026-03-25 · Zhuoran Li, Zhiyang Li, Kaijun Zhou, Jinyu Gu

Research Track A · General AI

Despite the promise of Vision-Language-Action (VLA) models as generalist robotic controllers, their robustness against perceptual noise and environmental variations in out-of-distribution (OOD) tasks remains fundamentally limited by the absence of long-term memory, causal failure attribution, and dynamic intervention c…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.3

SPARK-IL: Spectral Retrieval-Augmented RAG for Knowledge-driven Deepfake Detection via Incremental Learning

2026-04-04 · Hessen Bougueffa Eutamene, Abdellah Zakaria Sellam, Abdelmalik Taleb-Ahmed, Abdenour Hadid

Research Track A · General AI

Detecting AI-generated images remains a significant challenge because detectors trained on specific generators often fail to generalize to unseen models; however, while pixel-level artifacts vary across models, frequency-domain signatures exhibit greater consistency, providing a promising foundation for cross-generator…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.3

Paper Espresso: From Paper Overload to Research Insight

2026-04-06 · Mingzhe Du, Luu Anh Tuan, Dong Huang, See-kiong Ng

Research Track A · General AI

The accelerating pace of scientific publishing makes it increasingly difficult for researchers to stay current. We present Paper Espresso, an open-source platform that automatically discovers, summarizes, and analyzes trending arXiv papers. The system uses large language models (LLMs) to generate structured summaries w…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.3

LIFE -- an energy efficient advanced continual learning agentic AI framework for frontier systems

2026-04-14 · Anne Lee, Gurudutt Hosangadi

Research Track A · General AI

The rapid advancement of AI has changed the character of HPC usage such as dimensioning, provisioning, and execution. Not only has energy demand been amplified, but existing rudimentary continual learning capabilities limit ability of AI to effectively manage HPCs. This paper reviews emerging directions beyond monolith…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.3

HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents

2026-04-18 · Jinchang Zhu, Jindong Li, Cheng Zhang, Jiahong Liu, Menglin Yang

Research Track A · General AI

Long-term memory is a critical challenge for Large Language Model agents, as fixed context windows cannot preserve coherence across extended interactions. Existing memory systems represent conversation history as unstructured embedding vectors, retrieving information through semantic similarity. This paradigm fails to …

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.3

Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning

2026-04-19 · Ziqing Zhuang, Linhai Zhang, Jiasheng Si, Deyu Zhou, Yulan He

Research Track A · General AI

Large language models (LLMs) have demonstrated strong reasoning capabilities, and as existing approaches for enhancing LLM reasoning continue to mature, increasing attention has shifted toward meta-reasoning as a promising direction for further improvement. However, most existing meta-reasoning methods remain episodic:…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.3

MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models

2026-06-08 · Hao Shi, Weiye Li, Bin Xie, Yulin Wang, Renping Zhou, Tiancai Wang, Xiangyu Zhang, Ping Luo, Gao Huang

Research Track A · General AI

Temporal modeling is essential for robotic manipulation, as effective control requires both memory of past interactions and imagination of future states. However, most VLA models rely primarily on the current observation and therefore struggle with long-horizon, temporally dependent tasks. Cognitive science suggests th…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.3

Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models

2026-06-17 · Nikita Kachaev, Andrey Moskalenko, Matvey Skripkin, Nikita Kurlaev, Daria Pugacheva, Albina Burlova, Mikhail Kolosov, Denis Shepelev, Andrey Kuznetsov, Elena Tutubalina, Aleksandr I. Panov, Alexey K. Kovalev, Vlad Shakhuro

Research Track A · General AI

Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalizat…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.2

An Approach for a Supporting Multi-LLM System for Automated Certification Based on the German IT-Grundschutz

2026-06-24 · Lea Roxanne Muth, Marian Margraf

Research Track A · General AI

This paper presents a novel approach to perform semi-automated BSI IT-Grundschutz certification using a MultiLarge Language Model system (MLS) with Hybrid RetrievalAugmented Generation (HybridRAG). Facing the challenges of the Network and Information Security Directive 2 (NIS2) directive, a shortage of specialists, and…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.0

Bi-CRCL: Bidirectional Conservative-Radical Complementary Learning with Pre-trained Foundation Models for Class-incremental Medical Image Analysis

2026-03-24 · Xinyao Wu, Zhe Xu, Cheng Chen, Jiawei Ma, Yefeng Zheng, Raymond Kai-yu Tong

Research Track A · General AI

Class-incremental learning (CIL) in medical image-guided diagnosis requires retaining prior diagnostic knowledge while adapting to newly emerging disease categories, which is critical for scalable clinical deployment. This problem is particularly challenging due to heterogeneous data and privacy constraints that preven…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 11.0

Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge

2026-04-08 · Wonseon Lim, Jaesung Lee, Dae-Won Kim

Research Track A · General AI

Continual learning (CL) on edge devices requires not only high accuracy but also training-time efficiency to support on-device adaptation under strict memory and computational constraints. While prompt-based continual learning (PCL) is parameter-efficient and achieves competitive accuracy, prior work has focused mainly…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.0

Mistake gating leads to energy and memory efficient continual learning

2026-04-15 · Aaron Pache, Mark CW van Rossum

Research Track A · General AI

Synaptic plasticity is metabolically expensive, yet animals continuously update their internal models without exhausting energy reserves. However, when artificial neural networks are trained, the network parameters are typically updated on every sample that is presented, even if the sample was classified correctly. Ins…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.0

Autonomous Drift Learning in Data Streams: A Unified Perspective

2026-05-02 · Xiaoyu Yang, En Yu, Jie Lu

Research Track A

In the pursuit of autonomous learning systems, the foundational assumption of stationarity, the premise that data distributions and model behaviors remain constant, is fundamentally untenable. Historically, the research community has addressed non-stationary environments almost exclusively under the scope of concept dr…

Review
pending
Role
unreviewed
Read
now
huggingface Score 11.0

BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models

2026-05-07 · Xin Gao, Ruiyi Zhang, Meixi Du, Peijia Qin, Pengtao Xie

Research Track A · General AI

Despite the success of large language models (LLMs) on general-purpose tasks, their performance in highly specialized domains such as biomedicine remains unsatisfactory. A key limitation is the inability of LLMs to effectively leverage biomedical tools, which clinical experts and biomedical researchers rely on extensiv…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.0

On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR

2026-05-07 · Hao Ye, Jisheng Dang, Junfeng Fang, Bimei Wang, Yizhou Zhang, Ning Lv, Wencan Zhang, Hong Peng, Bin Hu, Tat-Seng Chua

Research Track A · General AI

Recent extensive research has demonstrated that the enhanced reasoning capabilities acquired by models through Reinforcement Learning with Verifiable Rewards (RLVR) are primarily concentrated within the rank-1 components. Predicated on this observation, we employed Periodic Rank-1 Substitution and identified a counteri…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.0

Understanding Data Temporality Impact on Large Language Models Pre-training

2026-05-21 · Pilchen Hippolyte, Fabre Romain, Signe Talla Franck, Perez Patrick, Grave Edouard

Research Track A · General AI

Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal grounding remains poorly understood. In this work, we study the impact of pre-training dynamics on the acquisition of time-sensitive factual knowledge, focusing specifically…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.9

Can Scale Save Us From Plasticity Loss in Large Language Models?

2026-06-23 · J. Fernando Hernandez-Garcia, Tomás Figliolia, Beren Millidge

Research Track A · General AI

The loss of plasticity - the ability of a network to learn new information after having already learned older information - is a fundamental challenge in creating artificial neural networks capable of continual learning. Although this phenomenon has been known for decades, it has mostly been studied in older, relativel…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

Evidence of an Emergent "Self" in Continual Robot Learning

2026-03-25 · Adidev Jhunjhunwala, Judah Goldfeder, Hod Lipson

Research Track A

A key challenge to understanding self-awareness has been a principled way of quantifying whether an intelligent system has a concept of a "self," and if so how to differentiate the "self" from other cognitive structures. We propose that the "self" can be isolated by seeking the invariant portion of cognitive process th…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 10.5

SNID-SAGE: A Modern Framework for Interactive Supernova Classification and Spectral Analysis

2026-03-30 · Fiorenzo Stoppa, Stephen J. Smartt

Research Track A

We present SNID-SAGE (SuperNova IDentification-Spectral Analysis and Guided Exploration), a framework for supernova spectral classification with both a fully interactive graphical interface and a scriptable command-line pipeline for large-scale processing. The pipeline combines deterministic spectral preprocessing, FFT…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

A Semantic Geometry for Uncovering Paradigm Dynamics via Scientific Publications

2026-04-16 · Jinchang Liu, Qingshan Zhou, Hongkan Chen, Yi Bu

Research Track A

Science advances not only by accumulating discovered patterns but by changing how new problems and solutions are expressed. While structural indicators track scholarly attention, they offer only an indirect proxy for the reorganization of meaning. We propose a semantic geometry based on the R-P-C (references, focal pub…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation

2026-04-18 · Jiaxin Zhang, Xiangyu Peng, Qinglin Chen, Qinyuan Ye, Caiming Xiong, Chien-Sheng Wu

Research Track A

On-policy distillation (OPD) is an increasingly important paradigm for post-training language models. However, we identify a pervasive Scaling Law of Miscalibration: while OPD effectively improves task accuracy, it systematically traps models in severe overconfidence. We trace this failure to an information mismatch: t…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

Enhancing Continual Learning of Vision-Language Models via Dynamic Prefix Weighting

2026-04-20 · Hyeonseo Jang, Hyuk Kwon, Kibok Lee

Research Track A

We investigate recently introduced domain-class incremental learning scenarios for vision-language models (VLMs). Recent works address this challenge using parameter-efficient methods, such as prefix-tuning or adapters, which facilitate model adaptation to downstream tasks by incorporating task-specific information int…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

2026-04-22 · Shanshan Zhong, Yi Lu, Jingjie Ning, Yibing Wan, Lihan Feng, Yuyi Ao, Leonardo F. R. Ribeiro, Markus Dreyer, Sean Ammirati, Chenyan Xiong

Research Track A · General AI

Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how to learn them automatically and effectively remains unclear. We introduce SkillLearnBench, the first benchmark for evaluating continual skill learning methods, compris…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

NORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning

2026-04-29 · Karthik Charan Raghunathan, Christian Metzner, Laura Kriener, Melika Payvand

Research Track A · General AI

In a continual learning setting, we require a model to be plastic enough to learn a new task and stable enough to not disturb previously learned capabilities. We argue that this dilemma has an architectural root. A finite network has limited representational and plastic resources, yet the required capacity depends on p…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry

2026-04-30 · Kathrin Korte, Joachim Winter Pedersen, Eleni Nisioti, Sebastian Risi

Research Track A

To preserve previously learned representations, continual learning systems must strike a balance between plasticity, the ability to acquire new knowledge, and stability. This stability-plasticity dilemma affects how representations can be reused across tasks: shared structure enables transfer when tasks are similar but…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

Beyond Forgetting in Continual Medical Image Segmentation: A Comprehensive Benchmark Study

2026-05-07 · Bomin Wang, Hangqi Zhou, Yibo Gao, Xiahai Zhuang

Research Track A · General AI

Continual learning (CL) is essential for deploying medical image segmentation models in clinical environments where imaging domains, anatomical targets, and diagnostic tasks evolve over time. However, continual segmentation still faces three main challenges. First, the scenarios for this task remain insufficiently stan…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

Mela: Test-Time Memory Consolidation based on Transformation Hypothesis

2026-05-11 · Lungchuan Chen

Research Track A · General AI

Memory consolidation, the process by which transient experiences are transformed into stable, structured representations, is a foundational organizing principle in the human brain, yet it remains largely unexplored as a design principle for modern sequence models. In this work, we leverage established neuroscientific t…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression

2026-05-28 · Yilun Yao, Jiaming Pan, Elsie Dai, Peizhuang Cong, Yaoming Li, Tong Yang

Research Track A · General AI

Mixture-of-Experts (MoE) language models reduce per-token computation but still require storing and serving all experts, making deployment memory-intensive. Existing post-training compression methods mainly shrink this cost by pruning experts or merging their weights. We formulate post-training MoE compression as exper…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability

2026-06-04 · Seyed Arshan Dalili, Mehrdad Mahdavi

Research Track A · General AI

Sparse Autoencoders (SAEs) are widely used for mechanistic interpretability in large language models, yet their formulation assigns each latent feature a single decoder direction, implicitly assuming features to be one-dimensional. We show that this assumption mismatches with the multi-dimensional structure of model fe…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

When Robots Sleep: Offline Skill Consolidation for Shared-Policy Robot Learning

2026-06-16 · Nethmi Jayasinghe, Diana Gontero, Amit Ranjan Trivedi

Research Track A · General AI

Robots that learn over long deployments must add new skills without losing the shared policy structure that makes earlier skills reusable. We study sequential robot skill learning, where previous trajectories and task losses may be unavailable, and the deployed policy must remain a single shared controller without task…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.5

Scalable Behaviour Cloning on Browser Using via Skill Distillation

2026-06-30 · Kaisen Yang, Zheng Jiang, Yuzhao Peng, Houde Qian, Boshi Zhang, Youjie Zheng, Shijin Hong, Qingle Liu, Ruoyu Han, Bohan Lyu, Bingxiang He, Eren Cai, Calvin Xiao, Qinhuai Na

Research Track A · Research Track B · General AI

Internet users collectively perform an enormous range of skilled work through web browsers, from software development and document editing to search, forms, and enterprise workflows, making human browsing a highly scalable but under-exploited source of reusable browser skills. We argue that the bottleneck for browser a…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 10.3

Machine Collective Intelligence for Explainable Scientific Discovery

2026-04-30 · Gyoung S. Na, Chanyoung Park

Research Track A · General AI

Deriving governing equations from empirical observations is a longstanding challenge in science. Although artificial intelligence (AI) has demonstrated substantial capabilities in function approximation, the discovery of explainable and extrapolatable equations remains a fundamental limitation of modern AI, posing a ce…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.0

STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems

2026-03-22 · Alfred Shen, Aaron Shen

Research Track A · General AI

Current AI agent frameworks commit early to a single interaction protocol, a fixed tool integration strategy, and static user models, limiting their deployment across diverse interaction paradigms. To address these constraints, we introduce STEM Agent (Self-adapting, Tool-enabled, Extensible, Multi-agent), a modular ar…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 10.0

Learn by Surprise, Commit by Proof

2026-04-02 · Kang-Sin Choi

Research Track A · General AI

We propose LSCP, a self-gated post-training framework for autonomous knowledge acquisition: learning only what a model does not already know, verified against what it does know, at a strength proportional to conviction, with no external oracle. When a passage produces anomalously high per-token loss, LSCP flags it, gen…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.0

Fast Heterogeneous Serving: Scalable Mixed-Scale LLM Allocation for SLO-Constrained Inference

2026-04-08 · Jiaming Cheng, Duong Tung Nguyen

Research Track A · General AI

Deploying large language model (LLM) inference at scale requires jointly selecting base models, provisioning heterogeneous GPUs, configuring parallelism, and distributing workloads under tight latency, accuracy, and budget constraints. Exact mixed-integer linear programming (MILP) approaches guarantee optimality but sc…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.0

A Wasserstein Geometric Framework for Hebbian Plasticity

2026-04-17 · Ulrich Tan

Research Track A · General AI

We introduce the Tan-HWG framework (Hebbian-Wasserstein-Geometry), a geometric theory of Hebbian plasticity in which memory states are modeled as probability measures evolving through Wasserstein minimizing movements. Hebbian learning rules are formalized as Hebbian energies satisfying a sequential stability condition,…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.0

TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning

2026-06-04 · Marius Dragoi, Ioana Pintilie, Alexandra Dragomir, Antonio Barbalau, Florin Brad

Research Track A

Parameter-efficient finetuning methods based on spectral decomposition have enabled progress in Continual Learning. In this paper we introduce TailLoR, which utilizes the singular bases U and V of the pre-trained weights as a fixed reference frame to learn a low-rank update applied to the singular value matrix. A soft …

Review
pending
Role
unreviewed
Read
now
arxiv Score 9.5

RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots

2026-03-04 · Soroush Nasiriany, Sepehr Nasiriany, Abhiram Maddukuri, Yuke Zhu

Research Track A · General AI

Recent advances in robot learning have accelerated progress toward generalist robots that can perform everyday tasks in human environments. Yet it remains difficult to gauge how close we are to this vision. The field lacks a reproducible, large-scale benchmark for systematic evaluation. To fill this gap, we present Rob…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.5

DIET: Learning to Distill Dataset Continually for Recommender Systems

2026-03-26 · Jiaqing Zhang, Hao Wang, Mingjia Yin, Bo Chen, Qinglin Jia, Rui Zhou, Ruiming Tang, ChaoYi Ma, Enhong Chen

Research Track A · General AI

Modern deep recommender models are trained under a continual learning paradigm, relying on massive and continuously growing streaming behavioral logs. In large-scale platforms, retraining models on full historical data for architecture comparison or iteration is prohibitively expensive, severely slowing down model deve…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 9.5

Less Detail, Better Answers: Degradation-Driven Prompting for VQA

2026-04-06 · Haoxuan Han, Weijie Wang, Zeyu Zhang, Yefei He, Bohan Zhuang

Research Track A · General AI

Recent advancements in Vision-Language Models (VLMs) have significantly pushed the boundaries of Visual Question Answering (VQA).However,high-resolution details can sometimes become noise that leads to hallucinations or reasoning errors. In this paper,we propose Degradation-Driven Prompting (DDP), a novel framework tha…

Review
pending
Role
unreviewed
Read
now
arxiv Score 9.5

ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing

2026-04-23 · Jebacyril Arockiaraj, Dhruv Parikh, Viktor Prasanna

Research Track A · General AI

On-device continual learning (CL) is critical for edge AI systems operating on non-stationary data streams, but most existing methods rely on backpropagation or exemplar-heavy classifiers, incurring substantial compute, memory, and latency overheads. Hyperdimensional computing (HDC) offers a lightweight alternative thr…

Review
pending
Role
unreviewed
Read
now
arxiv Score 9.5

Shortcut Solutions Learned by Transformers Impair Continual Compositional Reasoning

2026-05-06 · William T. Redman, Erik C. Johnson, Brian Robinson

Research Track A · General AI

Identifying and exploiting common features across domains is at the heart of the human ability to make analogies, and is believed to be crucial for the ability to continually learn. To do this successfully, general and flexible computational strategies must be developed. While the extent to which Transformer neural net…

Review
pending
Role
unreviewed
Read
now
arxiv Score 9.5

Scene-Adaptive Continual Learning for CSI-based Human Activity Recognition with Mixture of Experts

2026-05-07 · Wenhan Zheng, Yuyi Mao, Ivan Wang-Hei Ho

Research Track A

Channel state information (CSI)-based human activity recognition (HAR) is vulnerable to performance degradation under domain shifts across varying physical environments. Continual learning (CL) offers a principled way to learn new domains sequentially while preserving past knowledge, but existing CL solutions for CSI-b…

Review
pending
Role
unreviewed
Read
now
huggingface Score 9.5

EarlyTom: Early Token Compression Completes Fast Video Understanding

2026-05-28 · Hesong Wang, Xin Jin, Lu Lu, Chenhaowen Li, Jian Chen, Qiang Liu, Huan Wang

Research Track A · General AI

Video large language models (Video-LLMs) have demonstrated strong capabilities in video understanding tasks. However, their practical deployment is still hindered by the inefficiency introduced by processing massive amounts of visual tokens. Although recent approaches achieve extremely low token retention ratios while …

Review
pending
Role
unreviewed
Read
now
arxiv Score 9.5

TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning

2026-05-29 · Xiaosong Han, Ke Chen, Xindi Dai, Di Liang, Minlong Peng, Wei Pang, Fausto Giunchiglia, Xiaoyue Feng, Yonghao Liu, Renchu Guan

Research Track A · General AI

In real-world deployment, LLMs are often adapted continually across tasks to keep LLMs up-to-date in production, where new fine-tuning should preserve previously learned skills. However, indiscriminately mixing tasks can dilute task specialization, while sequential fine-tuning (full-parameter or low rank adaptation) of…

Review
pending
Role
unreviewed
Read
now
arxiv Score 9.5

FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion

2026-06-09 · Yu Lu, Junjie Yang, Piotr Koniusz, YuXin Song, Yi Yang

Research Track A · General AI

Autoregressive video generators synthesize long videos by generating successive temporal segments, but their historical KV cache grows with video length. Existing bounded-cache methods reduce this cost with local windows, sink tokens, or compressed memory states, yet they usually assign fixed roles to different parts o…

Review
pending
Role
unreviewed
Read
now
huggingface Score 9.5

ActWorld: From Explorable to Interactive World Model via Action-Aware Memory

2026-06-16 · Zhexiao Xiong, Yizhi Song, Hao Kang, Qing Yan, Liming Jiang, Jenson Yang, Zhoujie Fu, Stathi Fotiadis, Angtian Wang, Zichuan Liu, Bo Liu, Yiding Yang, Xin Lu, Nathan Jacobs

Research Track A · General AI

Interactive world models aim to simulate environment dynamics under real-time user actions. However, their action vocabulary is largely confined to navigation: most actions correspond to motion (e.g., walk, turn, look around), while interaction with objects in the scene (e.g., pick up plates, open doors, or trigger phy…

Review
pending
Role
unreviewed
Read
now
arxiv Score 9.3

Cognitive Dark Matter: Measuring What AI Misses

2026-03-03 · Patrick J. Mineault, Thomas L. Griffiths, Sean Escola

Research Track A · General AI

We propose that the jagged intelligence landscape of modern AI systems arises from a missing training signal that we call "cognitive dark matter" (CDM): brain functions that meaningfully shape behavior yet are hard to infer from behavior alone. We identify key CDM domains-metacognition, cognitive flexibility, episodic …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.3

SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents

2026-04-19 · Ziao Zhang, Kou Shi, Shiting Huang, Avery Nie, Yu Zeng, Yiming Zhao, Zhen Fang, Qishen Su, Haibo Qiu, Wei Yang, Qingnan Ren, Shun Zou, Wenxuan Huang, Lin Chen, Zehui Chen, Feng Zhao

Research Track A · General AI

As the capability frontier of autonomous agents continues to expand, they are increasingly able to complete specialized tasks through plug-and-play external skills. Yet current benchmarks mostly test whether models can use provided skills, leaving open whether they can discover skills from experience, repair them after…

Review
pending
Role
unreviewed
Read
now
arxiv Score 9.3

Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft

2026-04-27 · Zhou Ziheng, Huacong Tang, Jinyuan Zhang, Haowei Lin, Bangcheng Yang, Qian Long, Fang Sun, Yizhou Sun, Yitao Liang, Ying Nian Wu, Demetri Terzopoulos, Xiaofeng Gao

Research Track A · General AI

Discovering causal regularities and applying them to build functional systems--the discovery-to-application loop--is a hallmark of general intelligence, yet evaluating this capacity has been hindered by the vast complexity gap between scientific discovery and real-world engineering. We introduce SciCrafter, a Minecraft…

Review
pending
Role
unreviewed
Read
now
arxiv Score 9.3

Learning All-Terrain Locomotion for a Planetary Rover with Actively Articulated Suspension

2026-06-05 · Arthur Bouton, Tristan D. Hasseler, Michael Paton, Travis Brown, Jacob Levy, William Reid, Joshua Martin, Hari Nayar

Research Track A · General AI

This paper presents ERNEST, a four-wheeled planetary rover concept equipped with a two-degree-of-freedom Active Gimbal Suspension that combines yaw and roll actuation to enable wheel reconfiguration, steering, and active load redistribution. A single neural network controller, trained to track a desired path across cha…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.0

Similarity-Aware Mixture-of-Experts for Data-Efficient Continual Learning

2026-03-24 · Connor Mclaughlin, Nigel Lee, Lili Su

Research Track A

Machine learning models often need to adapt to new data after deployment due to structured or unstructured real-world dynamics. The Continual Learning (CL) framework enables continuous model adaptation, but most existing approaches either assume each task contains sufficiently many data samples or that the learning tas…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.0

Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding

2026-04-09 · Mu Nan, Muquan Yu, Weijian Mai, Jacob S. Prince, Hossein Adeli, Rui Zhang, Jiahang Cao, Benjamin Becker, John A. Pyles, Margaret M. Henderson, Chunfeng Song, Nikolaus Kriegeskorte, Michael J. Tarr, Xiaoqing Hu, Andrew F. Luo

Research Track A · General AI

Visual decoding from brain signals is a key challenge at the intersection of computer vision and neuroscience, requiring methods that bridge neural representations and computational models of vision. A field-wide goal is to achieve generalizable, cross-subject models. A major obstacle towards this goal is the substanti…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.0

TCL: Enabling Fast and Efficient Cross-Hardware Tensor Program Optimization via Continual Learning

2026-04-14 · Chaoyao Shen, Linfeng Jiang, Yixian Shen, Tao Xu, Guoqing Li, Anuj Pathania, Andy D. Pimentel, Meng Zhang

Research Track A

Deep learning (DL) compilers rely on cost models and auto-tuning to optimize tensor programs for target hardware. However, existing approaches depend on large offline datasets, incurring high collection costs and offering suboptimal transferability across platforms. In this paper, we introduce TCL, a novel efficient an…

Review
pending
Role
unreviewed
Read
now
arxiv Score 9.0

Adaptive Unknown Fault Detection and Few-Shot Continual Learning for Condition Monitoring in Ultrasonic Metal Welding

2026-04-15 · Ahmadreza Eslaminia, Kuan-Chieh Lu, Klara Nahrstedt, Chenhui Shao

Research Track A

Ultrasonic metal welding (UMW) is widely used in industrial applications but is sensitive to tool wear, surface contamination, and material variability, which can lead to unexpected process faults and unsatisfactory weld quality. Conventional monitoring systems typically rely on supervised learning models that assume a…

Review
pending
Role
unreviewed
Read
now
arxiv Score 9.0

IORM: Hierarchical I/O Governance for Thousands of Consolidated Databases on Oracle Exadata

2026-05-27 · Rajarshi Chowdhury, Akshay Shah, Zakaria Alrmaih, Chenhao Guo, Anubhav Singh, Sue Lee

Research Track A · General AI

Oracle Exadata consolidates thousands of tenant databases onto shared storage infrastructure deployed at hundreds of customer sites worldwide. Oracle Multitenant architecture enables this extreme density, with thousands of tenant databases sharing a single Exadata storage system -- but this creates a multi-level resour…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.0

In-Context Reward Adaptation for Robust Preference Modeling

2026-05-28 · Zhenyu Sun, Zheng Xu, Ermin Wei

Research Track A · General AI

Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. However, human values are inherently diverse and heterogeneous, and a single reward model often lacks the robustness required to generalize to unseen preference domains. Whil…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.0

CloudCons: A Comprehensive End-to-End Benchmark for Cloud Resource Consolidation

2026-06-11 · Xiaobin Zhang, Lefei Shen, Mouxiang Chen, Zhuo Li, Hongkai Li, Han Fu, Jianling Sun, Xiaoxue Ren, Chenghao Liu

Research Track A · General AI

Driven by conservative over-provisioning to guarantee service reliability, resource utilization in cloud data centers remains at low levels. To mitigate this, the forecast-then-optimize paradigm has emerged to optimize consolidation by anticipating future demands. While emerging time series foundation models promise to…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.0

A Compositional Framework for Open-ended Intelligence

2026-06-13 · Ida Momennejad, Roberta Raileanu

Research Track A

Open-ended intelligence is the capacity to adapt to novel problems and environments that are substantially different from those in training. A mathematics of open-ended intelligence requires two pillars: first, a minimal set of representational primitives (e.g., states, actions) and algorithmic primitives (e.g., neares…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.0

SCAN: A Decision-Making Framework for Effective Task Allocation with Generative AI

2026-06-14 · Fendi Tsim, Alina Gutoreva

Research Track A

We introduce SCAN -- a human-centric decision-making framework to facilitate learners for effective task allocation with Generative Artificial Intelligence (GenAI) based on Vygotsky's Zone of Proximal Development and Metacognition. In SCAN, we systematize and formalize AI-human interaction by introducing a task-identif…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.0

Energy-Aware Scheduling for Serverless LLM Serving on Shared GPUs

2026-06-29 · Tianyu Wang, Gourav Rattihalli, Aditya Dhakal, Longfei Shangguan, Dejan Milojicic

Research Track A

As LLM inference becomes a major cloud workload, its growing energy footprint makes cluster-wide energy optimization increasingly important. Serverless LLM serving helps platforms absorb traffic volatility by elastically sharing GPU resources across models, but this sharing also makes energy optimization difficult. Mul…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.5

Alertness Optimization for Shift Workers Using a Physiology-based Mathematical Model

2026-03-30 · Zidi Tao, A. Agung Julius, John T Wen

Research Track A

Sleep is vital for maintaining cognitive function, facilitating metabolic waste removal, and supporting memory consolidation. However, modern societal demands, particularly shift work, often disrupt natural sleep patterns. This can induce excessive sleepiness among shift workers in critical sectors such as healthcare a…

Review
pending
Role
unreviewed
Read
now
arxiv Score 8.5

Lyra 2.0: Explorable Generative 3D Worlds

2026-04-14 · Tianchang Shen, Sherwin Bahmani, Kai He, Sangeetha Grama Srinivasan, Tianshi Cao, Jiawei Ren, Ruilong Li, Zian Wang, Nicholas Sharp, Zan Gojcic, Sanja Fidler, Jiahui Huang, Huan Ling, Jun Gao, Xuanchi Ren

Research Track A

Recent advances in video generation enable a new paradigm for 3D scene creation: generating camera-controlled videos that simulate scene walkthroughs, then lifting them to 3D via feed-forward reconstruction techniques. This generative reconstruction approach combines the visual fidelity and creative capacity of video m…

Review
pending
Role
unreviewed
Read
now
arxiv Score 8.5

A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation

2026-04-15 · Julian Killingback, Ofer Meshi, Henry Li, Hamed Zamani, Maryam Karimzadehgan

Research Track A · General AI

Traditional Retrieval-Augmented Generation (RAG) approaches generally assume that retrieval and generation occur on powerful servers removed from the end user. While this reduces local hardware constraints, it introduces significant drawbacks: privacy concerns regarding data access, recurring maintenance and storage co…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.5

Learning Hippo: Multi-attractor Dynamics and Stability Effects in a Biologically Detailed CA3 Extension of Hopfield Networks

2026-04-22 · Daniele Corradetti, Renato Corradetti

Research Track A · General AI

We present a biologically detailed extension of the classical Hopfield/Marr auto-associative memory model for CA3, implementing ten populations (two asymmetric pyramidal subtypes, eight GABAergic interneuron classes), forty-seven compartments, multi-rule plasticity (recurrent Hebb, BCM anti-saturation, mossy-fiber shor…

Review
pending
Role
unreviewed
Read
now
huggingface Score 8.5

GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs

2026-05-07 · Pranav Mantini, Shishir K. Shah

Research Track A

We address the challenge of knowledge composition in Vision-Language Models (VLMs), where accumulating expertise across multiple domains or tasks typically leads to catastrophic forgetting. We introduce GeoStack (Geometric Stacking), a modular framework that allows independently trained domain experts to be composed in…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.5

Masked Generative Transformer Is What You Need for Image Editing

2026-05-11 · Wei Chow, Linfeng Li, Xian Sun, Lingdong Kong, Zefeng Li, Qi Xu, Hang Song, Tian Ye, Xian Wang, Jinbin Bai, Shilin Xu, Xiangtai Li, Junting Pan, Shaoteng Liu, Ran Zhou, Tianshu Yang, Songhua Liu

Research Track A · General AI

Diffusion models dominate image editing, yet their global denoising mechanism entangles edited regions with surrounding context, causing modifications to propagate into areas that should remain intact. We propose a fundamentally different approach by leveraging Masked Generative Transformers (MGTs), whose localized tok…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.5

Self-Regulated Learning in Essay Writing: Consistency of Strategies and Impact on Outcomes

2026-05-14 · Gloria Fernández-Nieto, Kiyoshige Garcés, Mladen Raković, Tongguang Li, Xinyu Li, Linxuan Zhao, Dragan Gašević

Research Track A

Background: Abilities for effective self-regulated learning (SRL) are critical for lifelong learning, particularly during adolescence when these skills consolidate and strongly influence future learning. Their importance has grown with the rise of online and blended education. Yet, little is known about how secondary s…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.5

Towards Explainability of SLMs by investigating Token Level Activation

2026-05-21 · Sayantani Ghosh, Rajashik Datta, Amit Kumar Das, Amlan Chakrabarti

Research Track A

Transformer-based language models such as BERT having 110M+ parameters have revolutionized natural language understanding, yet their internal mechanisms remain largely opaque to researchers and practitioners. Traditional attention-based interpretability methods often emphasize structurally important but semantically we…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.5

Developing a UXR Point of View for Cognitive Accessibility in Mobile Learning with Generative AI

2026-05-29 · Fatima Ahmad Muazu, Festus Adedoyin, Huseyin Dogan, Abiodun Adedeji, Melike Akca, Olumuyiwa Ayorinde

Research Track A · General AI

This study investigates how UX research (UXR) principles, combined with Large Language Model (LLM)-supported analysis, can be used to improve the quality of requirements for mobile learning systems designed for learners with cognitive disabilities. Using the UXR Point-of-View (PoV) pyramid as a methodological framework…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.3

Beyond Benchmarks: How Users Evaluate AI Chat Assistants

2026-03-26 · Moiz Sadiq Awan, Muhammad Haris Noor, Muhammad Salman Munaf

Research Track A · General AI

Automated benchmarks dominate the evaluation of large language models, yet no systematic study has compared user satisfaction, adoption motivations, and frustrations across competing platforms using a consistent instrument. We address this gap with a cross-platform survey of 388 active AI chat users, comparing satisfac…

Review
pending
Role
unreviewed
Read
now
arxiv Score 8.3

Safe Continual Reinforcement Learning in Non-stationary Environments

2026-04-21 · Austin Coursey, Abel Diaz-Gonzalez, Marcos Quinones-Grueiro, Gautam Biswas

Research Track A · General AI

Reinforcement learning (RL) offers a compelling data-driven paradigm for synthesizing controllers for complex systems when accurate physical models are unavailable; however, most existing control-oriented RL methods assume stationarity and, therefore, struggle in real-world non-stationary deployments where system dynam…

Review
pending
Role
unreviewed
Read
now
arxiv Score 8.3

Toward the Whole Picture: Accumulative Fingerprint Mapping and Reconstruction for Small-Area Mobile Sensors

2026-06-14 · Xiongjun Guan, Jianjiang Feng, Jie Zhou

Research Track A · General AI

Small-area fingerprint sensing on mobile devices creates a fundamental mismatch between acquisition and recognition: each touch captures only a tiny, pose-varying local patch, while reliable biometric matching ultimately requires a stable and sufficiently complete fingerprint representation. Existing pipelines largely …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.0

Associative Constructive Evolution: Enhancing Metaheuristics through Hebbian-Learned Generative Guidance

2026-03-31 · Shanxian Lin, Yuichi Nagata, Haichuan Yang

Research Track A

Metaheuristic algorithms such as Particle Swarm Optimization (PSO) and Evolutionary Algorithms (EA) excel at exploring solution spaces but lack mechanisms to accumulate and reuse procedural knowledge from successful search trajectories. This paper proposes Associative Constructive Evolution (ACE), a framework that enha…

Review
pending
Role
unreviewed
Read
now
arxiv Score 8.0

NetSecBed: A Container-Native Testbed for Reproducible Cybersecurity Experimentation

2026-04-05 · Leonardo Bitzki, Diego Kreutz, Tiago Heinrich, Douglas Fideles, Leandro Bertholdo, Silvio Quincozes, Angelo Diniz

Research Track A

Cybersecurity research increasingly depends on reproducible evidence, such as traffic traces, logs, and labeled datasets, yet most public datasets remain static and offer limited support for controlled re-execution and traceability, especially in heterogeneous multi-protocol environments. This paper presents NetSecBed,…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.0

Failure Ontology: A Lifelong Learning Framework for Blind Spot Detection and Resilience Design

2026-04-12 · Yuan Sun, Hong Yi, Jinyuan Liu

Research Track A

Personalized learning systems are almost universally designed around a single objective: help people acquire knowledge and skills more efficiently. We argue this framing misses the more consequential problem. The most damaging failures in human life-financial ruin, health collapse, professional obsolescence-are rarely …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.0

Physics-Informed Neural Networks for Methane Sorption: Cross-Gas Transfer Learning, Ensemble Collapse Under Physics Constraints, and Monte Carlo Dropout Uncertainty Quantification

2026-04-15 · Mohammad Nooraiepour, Zezhang Song, Wei Li, Sarah Perez

Research Track A

Accurate methane sorption prediction across heterogeneous coal ranks requires models that combine thermodynamic consistency, efficient knowledge transfer across data-scarce geological systems, and calibrated uncertainty estimates, capabilities that are rarely addressed together in existing frameworks. We present a phys…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.0

MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining

2026-04-27 · Phung Gia Huy, Hai An Vu, Minh-Phuc Truong, Thang Duc Tran, Linh Ngo Van, Thanh Hong Nguyen, Trung Le

Research Track A · General AI

Representation learning is fundamental to NLP, but building embeddings that work well at different computational budgets is challenging. Matryoshka Representation Learning (MRL) offers a flexible inference paradigm through nested embeddings; however, learning such structures requires explicit coordination of how inform…

Review
pending
Role
unreviewed
Read
now
arxiv Score 8.0

Continual Segmentation under Joint Nonstationarity

2026-05-19 · Prashant Pandey, Himanshu Kumar, Devineni Sri Venkatraya Chowdary, Brejesh Lall

Research Track A

Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision availability change simultaneously over time. This setting reflects practical structured prediction systems, yet remains largely unexplored in prior continual learning work…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 8.0

Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving

2026-06-15 · Hyungmin Kim, Minsoo Kim, Hongseok Kim, Jungwook Choi

Research Track A · General AI

Multi-turn LLM serving accumulates dialogue history whose Key-Value (KV) cache grows with every turn and every user, quickly exceeding the model weights themselves and making memory -- not compute -- the binding constraint on throughput. Non-uniform KV compression, which allocates heterogeneous budgets across attention…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.8

QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding

2026-04-28 · Shuxiang Cao, Zijian Zhang, Abhishek Agarwal, Grace Bratrud, Niyaz R. Beysengulov, Daniel C. Cole, Alejandro Gómez Frieiro, Elena O. Glen, Hao Hsu, Gang Huang, Raymond Jow, Greshma Shaji, Tom Lubowe, Ligeng Zhu, Luis Mantilla Calderón, Nicola Pancotti, Joel Pendleton, Brandon Severin, Charles Etienne Staub, Sara Sussman, Antti Vepsäläinen, Neel Rajeshbhai Vora, Yilun Xu, Varinia Bernales, Daniel Bowring, Elica Kyoseva, Ivan Rungger, Giulia Semeghini, Sam Stanwyck, Timothy Costa, Alán Aspuru-Guzik, Krysta Svore

Research Track A · General AI

Quantum computing calibration depends on interpreting experimental data, and calibration plots provide the most universal human-readable representation for this task, yet no systematic evaluation exists of how well vision-language models (VLMs) interpret them. We introduce QCalEval, the first VLM benchmark for quantum …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.8

On-Policy Replay for Continual Supervised Fine-Tuning

2026-05-28 · Yan Chen, Taojie Zhu, Meng Zhang, Xin Chen, Jiaqi Huang, Dongyang Xu, Yizhi Wang

Research Track A · General AI

Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting of earlier capabilities. Recent work shows that on-policy signals -- training on the model's own outputs -- reduce forgetting more reliably…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.5

LightTune: Lightweight Forward-Only Online Fine-Tuning with Applications to Link Adaptation

2026-04-14 · Ramy E. Ali, Federico Penna

Research Track A

Deploying machine learning (ML) algorithms on mobile phones is bottlenecked by performance degradation under dynamic, real-world conditions that differ from the offline training conditions. While continual learning and adaptation are essential to mitigate this distributional shift, conventional online learning methods …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.5

Neural Recovery of Historical Lexical Structure in Bantu Languages from Modern Data

2026-04-24 · Hillary Mutisya, John Mugane

Research Track A · General AI

We investigate whether neural models trained exclusively on modern morphological data can recover cross-lingual lexical structure consistent with historical reconstruction. Using BantuMorph v7, a transformer over Bantu morphological paradigms, we analyze 14 Eastern and Southern Bantu languages, extract encoder embeddin…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.5

OpenRoundup: Multi-Table Data Wrangling Through Interactive Visualization

2026-06-10 · Stephen Kasica, Charles Berret, Tamara Munzner

Research Track A

Data journalists routinely integrate records across multiple independently published sources to support accountability reporting, yet no existing interactive wrangling tool treats the collection of tables -- rather than the single table -- as its primary unit of work. We present OpenRoundup, an open-source, browser-bas…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.5

A Sustainable Integrated Framework for Multi-Type Urban Waste Collection and Recycling

2026-06-11 · Víctor Blanco, J. Fernando Camacho-Vallejo, Yolanda Hinojosa

Research Track A

Urban waste management faces increasing operational and environmental challenges driven by population growth, heterogeneous waste streams, traffic congestion, and the need for sustainable collection infrastructures. We present an integrated optimization framework for the design of multi-type urban waste collection and …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.5

Open-World Video Segmentation

2026-06-14 · Qing Su, Kaiyang Li, Yuan Zhuang, Fei Miao, Shihao Ji

Research Track A · General AI

While video segmentation has advanced rapidly on short clips and closed-set benchmarks, open-world video segmentation remains largely unexplored. The challenge is twofold: (1) existing methods are not designed to support object discovery and identity maintenance in long videos of dynamic ego-motion, and (2) existing ev…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.5

UoU: A Universal Fingerprint Foundation Model Based on Large-Scale Unsupervised Learning

2026-06-16 · Xiongjun Guan, Jianjiang Feng, Jie Zhou

Research Track A

Fingerprint recognition is still dominated by task-specific pipelines, where enhancement, structural parsing, alignment, and matching are optimized in isolation. Although effective in narrow settings, this design limits representation reuse across sensors, qualities, and downstream applications. We therefore present Uo…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.5

Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication

2026-06-17 · Wenqi Jia, Zhewen Hu, Ying Huang, Yu Gong, Stavros Kalafatis, Yuke Wang, Wei Niu, Chengming Zhang, Ang Li, Sheng Di, Yuede Ji, Bo Fang, Miao Yin

Research Track A

3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.3

CLSGen: A Dual-Head Fine-Tuning Framework for Joint Probabilistic Classification and Verbalized Explanation

2026-04-13 · WonJin Yoon, Kangyu Zhu, Ian Bulovic, Autumn Sehy, Yanjun Gao, Dmitriy Dligach, Majid Afshar, Timothy A. Miller

Research Track A · General AI

With the recent progress of Large Language Models (LLMs), there is a growing interest in applying these models to solve complex and challenging problems. Modern LLMs, capable of processing long contexts and generating verbalized explanations, offer significant potential in addressing real-world applications. However, a…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.3

Beyond Uniform Tokens: Adaptive Compression for Time Series Language Models

2026-06-11 · Jialin Gan, Xin Qiu, Guangzhe Chen, Xue Wang

Research Track A · General AI

Large language models (LLMs) have enabled time series (TS) analysis by jointly modeling numerical observations and textual context through a shared token interface. However, TS tokens and prompt tokens exhibit fundamentally different information structures, making uniform token processing inefficient. In this paper, we…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.0

CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs

2026-05-07 · Zhengru Fang, Yanan Ma, Yu Guo, Senkang Hu, Yixian Zhang, Hangcheng Cao, Wenbo Ding, Yuguang Fang

Research Track A · General AI

When a chest X-ray shows consolidation but the question asks which finding is present, a medical vision-language model may answer "No consolidation." This is more than an incorrect choice: it is a polarity reversal that emits a clinical statement contradicting the image. We study this failure as negated-option attracti…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.0

From Expansion to Consolidation: Socio-Spatial Contagion Dynamics in Off-Grid PV Adoption

2026-05-10 · Roni Blushtein-Livnon, Tal Svoray, Itay Fischhendler, Havatzelet Yahel, Emir Galilee

Research Track A

In traditional rural societies, where social ties are embedded in physical space, the diffusion of emerging technologies may be amplified through socio-spatial contagion (SSC). Such processes may play a key role in accelerating residential PV adoption in off-grid regions. Yet empirical evidence on SSC in PV adoption re…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.0

Distributed optimal control problems governed by poroelasticity equations

2026-05-29 · Arbaz Khan, Jeonghun J. Lee, Harpal Singh

Research Track A

In this paper, we propose and analyze a novel two-field symmetric formulation with solid displacement and fluid pressure as main unknowns for the Biot's consolidation model in poroelasticity. Firstly, we prove the well-posedness of the new formulation and then show the existence and uniqueness of optimal control where …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.5

GridVAD: Open-Set Video Anomaly Detection via Spatial Reasoning over Stratified Frame Grids

2026-03-26 · Mohamed Eltahir, Ahmed O. Ibrahim, Obada Siralkhatim, Tabarak Abdallah, Sondos Mohamed

Research Track A · General AI

Vision-Language Models (VLMs) are powerful open-set reasoners, yet their direct use as anomaly detectors in video surveillance is fragile: without calibrated anomaly priors, they alternate between missed detections and hallucinated false alarms. We argue the problem is not the VLM itself but how it is used. VLMs should…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.5

Dual-Stage Invariant Continual Learning under Extreme Visual Sparsity

2026-03-27 · Rangya Zhang, Jiaping Xiao, Lu Bai, Yuhang Zhang, Mir Feroskhan

Research Track A

Continual learning seeks to maintain stable adaptation under non-stationary environments, yet this problem becomes particularly challenging in object detection, where most existing methods implicitly assume relatively balanced visual conditions. In extreme-sparsity regimes, such as those observed in space-based residen…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.5

HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning

2026-03-27 · Xuerui Zhang, Xuehao Wang, Zhan Zhuang, Linglan Zhao, Ziyue Li, Xinmin Zhang, Zhihuan Song, Yu Zhang

Research Track A

Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams of homogeneous tasks (\textit{e.g.}, only classification tasks) and neglects the scenario of learning across heterogeneous tasks that posse…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.5

Auto-Stabilized Weak Galerkin Finite Element Methods for Biot's consolidation model on Non-Convex Polytopal Meshes

2026-03-29 · Chunmei Wang, Shangyou Zhang

Research Track A

This paper presents an auto-stabilized weak Galerkin (WG) finite element method for the Biot's consolidation model within the classical displacement-pressure two-field formulation. Unlike traditional WG approaches, the proposed scheme achieves numerical stability without the requirement of traditional stabilizers. Spat…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.5

Statehood Without Capacity

2026-04-13 · Rok Spruk

Research Track A

This paper develops a political-economy theory of statehood without capacity. I argue that under specific institutional and geopolitical conditions, a polity can become trapped in an equilibrium of nominal statehood: a state in which claims to sovereignty, external recognition, and symbolic legitimacy persist or even s…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.5

From Papers to Progress: Rethinking Knowledge Accumulation in Software Engineering

2026-04-17 · Jason Cusati, Chris Brown

Research Track A

Software engineering research has experienced rapid growth in both output and participation over the past decades. Yet concerns persist about the field's ability to accumulate, integrate, and reuse knowledge in ways that support long-term progress. To better understand how the community itself perceives these challenge…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.5

Analyzing Process Data from Computer-Based Assessments: A Tutorial on Preprocessing, Feature Extraction, and Model-Based Inference

2026-04-18 · Daeun Hwangbo, Junyeong Park, Minjeong Jeon, Ick Hoon Jin

Research Track A

Computer-based assessments routinely generate detailed interaction logs -- commonly referred to as process data -- that record every action a respondent performs during task completion, yet systematic preprocessing guidance, integrated analytical workflows, and cross-method consistency checks remain scarce in the liter…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.5

Can Institutional Integration of Western Balkans Stock Exchanges Strengthen Monetary Transmission?

2026-04-20 · Stefan Tanevski

Research Track A

This paper asks how institutional stock-market integration reshapes the transmission of monetary policy through asset prices in small open economies. Motivated by the persistent segmentation of Western Balkan capital markets, we develop a two-stage counterfactual transmission framework to identify how stock-exchange co…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 6.5

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

2026-05-29 · Stine Lyngsø Beltoft, William Brach, Federico Torrielli, Jacob Nielsen, Annemette Brok Pirchert, Filippo Tonini, Peter Schneider-Kamp, Lukas Galke Poech

Research Track A · General AI

Monitoring autonomous language model agents currently relies mostly on surface behavior. But what happens when agent populations invent new languages with the goal of avoiding human oversight. Here, we study the emergent languages on Moltbook. For this, we build upon the Moltbook Files dataset and apply a two-stage app…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.3

No Universal Courtesy: A Cross-Linguistic, Multi-Model Study of Politeness Effects on LLMs Using the PLUM Corpus

2026-04-17 · Hitesh Mehta, Arjit Saxena, Garima Chhikara, Rohit Kumar

Research Track A · General AI

This paper explores the response of Large Language Models (LLMs) to user prompts with different degrees of politeness and impoliteness. The Politeness Theory by Brown and Levinson and the Impoliteness Framework by Culpeper form the basis of experiments conducted across three languages (English, Hindi, Spanish), five mo…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.0

Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training

2026-04-02 · William Hoy, Binxu Wang, Xu Pan

Research Track A · General AI

Evolution Strategies (ES) have emerged as a scalable gradient-free alternative to reinforcement learning based LLM fine-tuning, but it remains unclear whether comparable task performance implies comparable solutions in parameter space. We compare ES and Group Relative Policy Optimization (GRPO) across four tasks in bot…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.0

TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning

2026-04-02 · Zhanting Zhou, KaHou Tam, Ziqiang Zheng, Zeyu Ma

Research Track A · General AI

Multimodal recommendation systems (MRS) jointly model user-item interaction graphs and rich item content, but this tight coupling makes user data difficult to remove once learned. Approximate machine unlearning offers an efficient alternative to full retraining, yet existing methods for MRS mainly rely on a largely uni…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.0

Exclusive Unlearning

2026-04-07 · Mutsumi Sasaki, Kouta Nakayama, Yusuke Miyao, Yohei Oseki, Masaru Isonuma

Research Track A · General AI

When introducing Large Language Models (LLMs) into industrial applications, such as healthcare and education, the risk of generating harmful content becomes a significant challenge. While existing machine unlearning methods can erase specific harmful knowledge and expressions, diverse harmful content makes comprehensiv…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.0

How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study

2026-04-16 · Zhen Yang, Ping Jian, Zhongbin Guo, Zuming Zhang, Chengzhi Li, Yonghong Deng, Xinyue Zhang, Wenpeng Lu

Research Track A

Over the past year, spatial intelligence has drawn increasing attention. Many prior works study it from the perspective of visual-spatial intelligence, where models have access to visuospatial information from visual inputs. However, in the absence of visual information, whether linguistic intelligence alone is suffici…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 5.5

Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development

2026-03-29 · Zhongying Deng, Cheng Tang, Ziyan Huang, Jiashi Lin, Ying Chen, Junzhi Ning, Chenglong Ma, Jiyao Liu, Wei Li, Yinghao Zhu, Shujian Gao, Yanyan Huang, Sibo Ju, Yanzhou Su, Pengcheng Chen, Wenhao Tang, Tianbin Li, Haoyu Wang, Yuanfeng Ji, Hui Sun, Shaobo Min, Liang Peng, Feilong Tang, Haochen Xue, Rulin Zhou, Chaoyang Zhang, Wenjie Li, Shaohao Rui, Weijie Ma, Xingyue Zhao, Yibin Wang, Kun Yuan, Zhaohui Lu, Shujun Wang, Jinjie Wei, Lihao Liu, Dingkang Yang, Lin Wang, Yulong Li, Haolin Yang, Yiqing Shen, Lequan Yu, Xiaowei Hu, Yun Gu, Yicheng Wu, Benyou Wang, Minghui Zhang, Angelica I. Aviles-Rivero, Qi Gao, Hongming Shan, Xiaoyu Ren, Fang Yan, Hongyu Zhou, Haodong Duan, Maosong Cao, Shanshan Wang, Bin Fu, Xiaomeng Li, Zhi Hou, Chunfeng Song, Lei Bai, Yuan Cheng, Yuandong Pu, Xiang Li, Wenhai Wang, Hao Chen, Jiaxin Zhuang, Songyang Zhang, Huiguang He, Mengzhang Li, Bohan Zhuang, Zhian Bai, Rongshan Yu, Liansheng Wang, Yukun Zhou, Xiaosong Wang, Xin Guo, Guanbin Li, Xiangru Lin, Dakai Jin, Mianxin Liu, Wenlong Zhang, Qi Qin, Conghui He, Yuqiang Li, Ye Luo, Nanqing Dong, Jie Xu, Wenqi Shao, Bo Zhang, Qiujuan Yan, Yihao Liu, Jun Ma, Zhi Lu, Yuewen Cao, Zongwei Zhou, Jianming Liang, Shixiang Tang, Qi Duan, Dongzhan Zhou, Chen Jiang, Yuyin Zhou, Yanwu Xu, Jiancheng Yang, Shaoting Zhang, Xiaohong Liu, Siqi Luo, Yi Xin, Chaoyu Liu, Haochen Wen, Xin Chen, Alejandro Lozano, Min Woo Sun, Yuhui Zhang, Yue Yao, Xiaoxiao Sun, Serena Yeung-Levy, Xia Li, Jing Ke, Chunhui Zhang, Zongyuan Ge, Ming Hu, Jin Ye, Zhifeng Li, Yirong Chen, Yu Qiao, Junjun He

Research Track A

Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical e…

Review
pending
Role
unreviewed
Read
soon