Research Paper Cockpit

Daily Digest - 2026-11-07

Papers first seen in this daily snapshot.

Daily Archives

Quick jump into generated daily digests.

Research Workflow

Latest digest: 2026-11-17.

Papers

73 visible entries

arxiv Score 29.9

PRISM-AMC: Replay-Free Continual Learning for Automatic Modulation Classification

2026-11-04 · Usman Akram, Matthew Graham, Haris Vikalo

Research Track A · General AI

Automatic modulation classification (AMC) is a key component of cognitive wireless systems, enabling spectrum awareness and adaptive communication. Most deep learning approaches to AMC assume a fixed set of modulation classes and access to previously observed training data. In practice, modulation classes and channel c…

Review
pending
Role
unreviewed
Read
now
arxiv Score 25.9

Modulating Merging Strengths via Joint Loss Estimation for LoRA-based Continual Learning

2026-11-03 · Kun Gu, De Cheng, Zhipeng Xu, Lingfeng He, Di Xu, Nannan Wang

Research Track A · General AI

Continual learning (CL) aims to adapt models to new tasks while preserving previously learned knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Efficient Fine-Tuning (PEFT) method, has gained increasing attention in CL due to its efficiency and scalability. Several LoRA-based merging methods m…

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.9

DLER: Dual-Logit Experience Replay for Online Continual Learning

2026-11-03 · Huiwei Lin, Shanshan Feng, Kong Aik Lee

Research Track A · General AI

Online continual learning aims to continuously train neural networks on a non-stationary data stream in a single pass. Rehearsal-based methods alleviate catastrophic forgetting by replaying stored samples, but the imbalance between current and previous data often leads to predictions biased toward current classes. Many…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.4

Securing Web Agents with the Compile-Then-Execute Paradigm

2026-11-04 · Annabella Chow, Jinhao Zhu, Sylvie Venuto, Abdulaziz Alharbi, Basel Alomair, Raluca Popa, David Wagner, Julien Piet

Research Track B · General AI

Web agents commonly follow the ReAct paradigm, selecting each action from runtime observations that inherently mix trusted and untrusted content. This design makes their control flow vulnerable to prompt injections embedded in webpages. We introduce Baya, a compile-then-execute web agent designed to prevent prompt-inje…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.9

JHiMA-WebRL: A Joint Hierarchical Multi-Agent Reinforcement Learning Framework for Long-Horizon Web Tasks

2026-11-03 · Shanka Subhra Mondal, Jiayun Wang

Research Track B · General AI

Multimodal web agents have shown promising capabilities for interacting with websites through graphical user interfaces (GUIs), yet realistic web tasks often require long-horizon, multi-step planning that remains challenging for monolithic policies. Such agents must jointly infer high-level plans, navigate through inte…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.2

NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinoma

2026-11-05 · Pengkai Wang, Wei-Wei Zhang, Yan Li, Min Tang, Zhitian Hou, Zeyu Liu, Guanghao Zhu, Yuanyi Wang, Yanggan Gu, Wenjun Wang, Minheng Ni, Congkai Xie, Zhijie Sang, Jianmin Wu, Ying Sun, Hongxia Yang

General AI

Current medical benchmarks typically break down clinical competence into isolated factual questions, single-image tasks, or static case vignettes. These tests score individual answers, but reveal less about whether a model can integrate subspecialty knowledge with multimodal evidence and track a patient's condition thr…

Review
pending
Role
unreviewed
Read
now
huggingface Score 18.0

OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery

2026-10-27 · Jiarui Yao, Ruida Wang, Tong Zhang

General AI

Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluating them on research-level problems remains challenging. We introduce OpenFrontiers, a cross-disciplinary resource that combines a structured corpus …

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.9

DRAP: Dynamics-Risk Adaptive Plasticity for Continual Learning in Physical AI

2026-11-03 · Oswaldo Ludwig

Research Track A · General AI

Continual learning in physical AI differs from conventional continual learning because small per-step policy errors can accumulate over a trajectory. Each deviation may move the agent outside the training distribution, increase subsequent prediction errors, and ultimately cause closed-loop task failure. This work intro…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.2

Voluntary Servitude: Weaponized Safety Warning Mechanisms for Controlling AI Agents

2026-11-03 · Ilan Zendel, Matan Levy, Stav Cohen, Avi Mendelson, Amit LeVi

Research Track B · General AI

LLM agents increasingly act on information retrieved from public sources they treat as credible, which turns a manipulated recommendation into a transaction, a dependency, or a decision with physical consequences. The security literature models this threat as instruction injection, in which an adversary writes a comman…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.2

Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation

2026-11-05 · Ali Sarabadani, Kheirolah Rahsepar Fard, Tahereh Jeirani

General AI

Large language models (LLMs) are increasingly used in biomedical and cognitive neuroscience, but their ability to reason reliably over heterogeneous knowledge graphs (KGs) remains unclear. We benchmark five LLMs (GPT-5.1, Gemini 2.0 Pro, Llama 3, Qwen, and BioGPT) across five KGs: DrugBank, NeuroSynth, Cognitive Atlas,…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.2

ProQuant: Progressive Quantization-aware Training for Edge MLLMs

2026-11-05 · Yufei Xue, Yushi Huang, Jiawei Shao, Pingcheng Dong, Yonghao Tan, Shiyao Li, Kwang-Ting Cheng, Jun Zhang

General AI

Multi-modal large language models (MLLMs) with impressive perception and understanding capabilities will enable a range of downstream applications. However, their substantial computational and memory requirements hinder the real-world implementation, particularly for resource-constrained edge devices. Quantization has …

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.8

What Is This Memory Useful For? Measuring Task-Conditioned Utility in Long-Term Agent Memory

2026-11-02 · Chih-Hsuan Yang, Anjir Ahmed Chowdhury, Feng Yan, Rajeev Thakur

Research Track A · General AI

A stored experience may answer one future question and offer little help with another. We measure this task-conditioned utility rather than assigning each memory a single importance score. A task-blind writer stores a memory without seeing the later task; a frozen reader then answers that task with and without the memo…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.2

RM-VLM: From Natural-Language Task Descriptions to Vision-Grounded Reward Machines

2026-11-05 · Roko Parac, Christos Ziakas, Leo Ardon, Alessandra Russo

General AI

Reward machines (RMs) have been proposed as a reward formulation in reinforcement learning (RL) to capture non-Markovian tasks where credit assignment depends on history. By representing reward functions as automata, RMs expose the task's temporal structure and allow such rewards to be handled within a Markovian framew…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.9

Human Motion Prediction via Continual Prior Compensation

2026-11-04 · Jianwei Tang, Jian-Fang Hu, Tianming Liang, Xiaotong Lin, Jiangxin Sun, Wei-Shi Zheng, Jianhuang Lai

Research Track A · General AI

Human Motion Prediction (HMP) aims to predict future human poses at different moments according to observed past motion sequences. Previous approaches mainly treated the prediction of different temporal moments as a single prediction task and learned the predictions of varied moments simultaneously, which would encount…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.2

Multimodal-SEA: Benchmarking AI Agent Security under Multimodal Social Engineering Attacks

2026-11-05 · Zhitao He, Chi Him Zhang, Chengru Han, Yi R Fung

General AI

Personal AI agents face social engineering attacks supported by forged multimodal content, but existing evaluations mainly focus on text-based dialogue, leaving their intrinsic security under such attacks insufficiently studied. We introduce Multimodal-SEA, an interactive benchmark comprising 608 expert-designed tasks …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.2

Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling

2026-11-05 · Xiaojun Wu, Cehao Yang, Xuhui Jiang, Chengjin Xu, Jia Li, Jian Guo

General AI

Mathematical modeling turns an open-ended real-world problem into assumptions, a model, a solution, and a defended recommendation, and its answers matter only if they are both close to a credible reference and physically feasible; existing benchmarks either score solver fragments or grade reports with an LLM judge, lea…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.2

The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI

2026-11-05 · Julian Kunkel, Ali Doosthosseini

General AI

Chat remains the default surface for many large language model (LLM) tasks, even as agentic tools such as OpenCode excel at coding and automation. Yet the model sees the current dialogue but not the workspace around it. We explore meta access---giving the assistant a structured, permissioned view of the interface itsel…

Review
pending
Role
unreviewed
Read
now
huggingface Score 15.0

Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents

2026-11-01 · Lang Mo, Xingxuan Zhang, Qi Wang, Mingchao Hao, Hao Yuan, Chunjing Gan, Wang Lu, Peng Cui

General AI

Agent decisions depend on empirical relationships that deployment observations reveal and task descriptions alone may leave unresolved. We introduce Decoupled Predictive Decision Making (DPDM), an architecture that formulates heterogeneous agent decisions as conditional prediction with a shared pretrained learner. Lang…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.4

MEMOIR: A Training-Free Memory Lifecycle for Long-Horizon LLM Agents

2026-11-05 · Mayank Anand, Subham Raj, Aman Vaibhav Jha, Sriparna Saha

Research Track A · General AI

Long-horizon LLM agents require memory systems that preserve useful information across sessions and retrieve it when needed. Existing systems treat these as separate problems: memories are written prospectively with static importance scores that are never revised after use. This creates two coupled failure modes: conso…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.9

Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment

2026-11-03 · Ariana M. Villegas-Suarez, Guido Freire, Sohan Venkatesh, Bartosz Cywiński

Research Track A · General AI

Fine-tuning a large language model (LLM) on harmful data in a narrow domain, such as bad medical advice, can make it broadly misaligned. How realistic this risk is remains unclear, since models are very rarely fine-tuned on explicitly harmful data in practice. In this work, we show that fine-tuning on data the model be…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.4

ViBench 2.0: A Benchmark for Long-Horizon Software Building

2026-11-03 · Daniel Furman, Preeya Kirani, Ibrahim Sheikh, Zhen Li, Peter Zhong, Michele Catasta

Research Track B · General AI

On Replit, our agentic engineering platform, users now build entire products without writing code, through successive feature requests to an agent. Yet existing coding benchmarks evaluate single, fully specified tasks, and many are near saturation. We introduce ViBench 2.0, a benchmark for long-horizon software buildin…

Review
pending
Role
unreviewed
Read
now
huggingface Score 13.4

Tools Need Not Speak in Text: Latent Context Compression for Agents

2026-11-04 · Yuetong Liu, Zhehao Zhou, Yitong Zhang, Haorui Chen, Jia Li

General AI

Large language model (LLM) agents typically append raw tool outputs to their context. Over multi-step interactions, long and noisy observations incur substantial context overhead and dilute the agent's attention to task-relevant information. Existing token pruning and summarization methods remain constrained by discret…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.2

CascadeFilter: Cost-Efficient Semantic Filtering with Joint Threshold Selection

2026-11-05 · Yanji He, Tao Zhong, Hongyang Chen, Xiaobo Zhang, Mingyu Yang, Wei Wang

General AI

Semantic filtering selects records that satisfy a natural-language predicate and is an important operation in data analytics based on large language models (LLMs). Executing an expensive model on every document incurs substantial inference cost. Existing approaches reduce this cost by accepting predictions from cheaper…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.2

CARE-FL: Federated Fine-Tuning of Multimodal LLMs in Resource-Constrained Edge Networks

2026-11-04 · Tianqi Zong, Baosheng Li, Nuocheng Yang, Binbin Chen, Marie Siew

General AI

Domain-specific adaptation of Multimodal Large Language Models (MLLMs) in privacy-sensitive edge environments requires federated fine-tuning, yet client selection remains challenging due to heterogeneous multimodal data and modality availability, dynamic system conditions, and evolving client utility during training. W…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.2

DelegateEval: Evaluating Platforms for Personal External Service Agents

2026-11-05 · Jichao Li, Jinrong Lu, Manjiang Yu, Zhixuan Liu

General AI

AI agents that work for an individual over time may also help that individual serve external clients. We define a personal external service agent as an agent authorized and continuously managed by a specific individual to accept client requests, deliver work, and provide ongoing support using that person's knowledge, e…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.2

Information Elicitation by Ordinal Agreement

2026-11-05 · Yiling Chen, Shi Feng, Grant Schoenebeck, Fang-Yi Yu

General AI

Ordinal information is central to tasks ranging from conference peer review to Reinforcement Learning from Human Feedback for large language models. In many such settings, there is no objective ground truth against which reports can be directly verified, making incentive-compatible elicitation challenging. Peer-predict…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.2

Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment

2026-11-05 · Yao Huang, Yifan Wang, Yitong Sun, Yichi Zhang, Yinpeng Dong

General AI

As LLM agents advance rapidly in autonomy, the risk of hidden objectives that bypass safety constraints becomes increasingly plausible. Chain-of-thought (CoT) monitoring offers a key control mechanism by reading the agent's reasoning and flagging misalignment before it materializes into action, yet its reliability depe…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.2

XStack: A Benchmark for ML Repo Migration

2026-11-05 · Linrong Cai, Taiming Lu, Haozhe Chen, Zhuang Liu

General AI

ML code should run where researchers choose, not where it was first written. Today, machine learning code mainly lives in two ecosystems, PyTorch on NVIDIA GPUs and JAX on Google TPUs. Migrating repositories between them means building and testing across frameworks and hardware. This migration is (1) a practical need, …

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.4

ScamWorld: An Interactive Environment for Evaluating Web Agents Against Online Fraud

2026-11-03 · Yutao Wu, Xiao Liu, Ming Wen, Hanxun Huang, Jun Wang, Xingjun Ma

Research Track B · General AI

Web agents increasingly browse, shop, and manage accounts on behalf of their users. Prior work has shown that they can be misled by adversarial content, including prompt injections and deceptive interfaces. Beyond such attacks, agents operating on the open web also encounter online fraud designed to deceive humans, inc…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.2

Automated Video-to-QA Pipeline: End-to-End Question Generation and Verification Using Large Language Models

2026-11-05 · Jaival Chauhan, Vikram Singh, Pruthwik Mishra

General AI

The exponential growth of educational and informational video content on platforms like YouTube presents a challenge for efficient knowledge retrieval and assessment. This paper proposes an end-to-end automated pipeline for extracting structured summaries and generating high-fidelity Question-Answer (QA) pairs from vid…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.2

Benchmarks as Software: Terminal-Bench and the Case for Continuous Benchmarks

2026-11-05 · E. Kelly Buchanan, Crystal Zhou, Scott W. Linderman, Christopher Ré

General AI

Coding agents are among the most economically consequential deployments of LLMs to date, making reliable evaluation increasingly important. Yet even benchmarks that are carefully validated at release can become stale. As models improve, they can discover valid solutions that existing verifiers reject, while changes to …

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.2

Enhancing Local and Global Structure in Compressed AI Agent Memory

2026-11-05 · Henry Han

General AI

AI agents store text as embedding vectors and compress them at scale. A compression is accepted when each item's nearest neighbors survive, but agents also consolidate, delete, and compare memories, tasks that depend on which items lie far apart. We evaluate both ends with two label-free fidelities from our prior work:…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.2

LABBA: LLM-Assisted Behavioral Biometric Authentication

2026-11-05 · Howard Halim, Eyasu Getahun Chekole, Jianying Zhou

General AI

Behavioral biometrics have emerged as a promising complement to traditional physiological biometrics by leveraging dynamic human characteristics. These modalities offer advantages including continuous authentication, inherent liveness detection, and greater resistance to credential theft and other spoofing attacks. How…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.2

SCALE: Real-Time Latent Communication for Cyber-Physical Agents

2026-11-05 · Shanghao Shi, Jian Xiao, Ching-Hsiang Chan, Sanjoy Baruah, Sastry Kompella, Yevgeniy Vorobeychik, William Yeoh, Ning Zhang

General AI

Latent communication enables agents to collaborate efficiently by directly exchanging intermediate model representations rather than raw sensor data or text messages. Existing approaches, however, are primarily designed for LLM agents and do not consider the bandwidth constraints and heterogeneous task deadlines faced …

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.2

SM4RT: Cascaded Feed-forward Model for 4D Reconstruction

2026-11-05 · Pang-Chi Lo, Jhao-Syun Lai, Tsung-Wei Ke

General AI

We introduce SM4RT, a multi-task cascade feed-forward model for dynamic scene reconstruction from RGB videos. While existing feed-forward approaches typically address geometry reconstruction and motion estimation separately--and often predict motions in a single coordinate frame that must account for camera movement--S…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.2

Should You Split Decode? Disaggregation Across Future Models and Accelerators

2026-11-05 · Ramyad Hadidi

General AI

For large language model (LLM) inference, prefill/decode disaggregation (P/D) is deployed in production to isolate phases with different resource demands. Attention/feed-forward network disaggregation (AFD) splits decode again, but adds communication, placement constraints, and another provisioned pool. We ask whether …

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.2

Social Humanoid: Socially Responsive Human-Humanoid Interaction

2026-11-05 · Vongani H. Maluleke, James Ni, Kie Horiuchi, Lea Wilken, Jiahui Lei, Evonne Ng, Roei Herzig, Jitendra Malik, Trevor Darrell, Angjoo Kanazawa

General AI

Humanoid robots are typically trained as solitary agents, leaving them unable to coordinate physically with human partners who naturally anticipate and adjust to one another. To bridge this gap, we present Social Humanoid, a hierarchical system that generates and executes socially responsive whole-body motion on a 29-D…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.2

Spectral and Subspace Dynamics of LoRA in Supervised Fine-Tuning and Reinforcement Learning

2026-11-05 · Chenruo Liu, Zihan Wang, Yijun Dong, Qi Lei

General AI

Low-rank adaptation (LoRA) is commonly used in both supervised fine-tuning (SFT) and reinforcement learning (RL), often under similar optimizer settings. Yet, how the different dynamics of the two stages manifest in the low-rank increment that LoRA optimizes remains unclear. Tracking the singular spectrum and subspaces…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.2

StrataFlux: Memory-Hierarchy-Native Low-Bit LLM Inference

2026-11-05 · Jake Hyun, Ziyu Zhao, Jae-sun Seo, Mohamed S. Abdelfattah

General AI

Quantization reduces the memory and bandwidth demands of large language model (LLM) inference but can degrade accuracy; offloading higher-precision data can instead stall generation. We introduce StrataFlux, a framework that challenges this tradeoff by recovering accuracy lost to low-bit weight and key-value (KV) cache…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.9

Continual Classification Beyond the Kernel Regime: Harnessing the Sparsity Bias of L2 Regularization in Diagonal Linear Networks

2026-11-04 · Gilad Karpel, Itay Evron, Ron Meir, Daniel Soudry

Research Track A

We study logistic regression for continual learning with linear predictors in a high-dimensional statistical setting. Existing theoretical work has largely focused on continual linear regression with variants of L2 regularization, motivated by their analytical simplicity and connection to the kernel regime of neural ne…

Review
pending
Role
unreviewed
Read
now
huggingface Score 10.4

Information Games: Strategic Crowding and Firm Repositioning in Language-Model Space

2026-11-05 · Marcus Gawronsky, Chun-Sung Huang

General AI

When firms respond to new market opportunities, their capacity choices alter the future discounted free cash flows available to both competitors and investors. In competitive markets, these investment decisions publicized in news articles and analyst reports, measuring the changes in capital structure, product mix, fir…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 10.4

Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout

2026-11-05 · Tushaar Gangavarapu, Gil Tabak, Clemens JS Schaefer

General AI

Linear attention compresses context into a fixed-size key-value state for linear-time training and constant-memory inference. Gated delta-rule models decay this state and erase its prediction for an incoming key before writing a new value; Gated DeltaNet-2 (GDN-2) generalizes this with channel-wise decay and decoupled,…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 10.4

Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens

2026-11-05 · Seongtae Hong, Youngjoon Jang, Jungseob Lee, Chanjun Park, Heuiseok Lim

General AI

Embedding models compress variable-length text into fixed-size vector representations, but this compression can entangle semantic content with residual token-level information, such as artifacts arising from attention sink behavior. We propose a simple method that prepends trainable [DUMP] tokens to the input during em…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 10.2

Scaffolding GenAI Use in Ethical Essay Writing: A Three-Year Experience Report in Introductory Computing

2026-11-05 · Asma Shakil, Paul Denny, Jun Seo, Gauravkumar Hirani, Sean Longyu Ma, Claus Brabrand

General AI

As society, ethics, and professional practice become increasingly integrated across the computer science curriculum, technical courses need practical ways to support ethical reasoning. Ethical essay assignments offer one approach, but little is known about how students use GenAI when writing such essays. This experienc…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.9

MKD2World: A Typed Spatial MarkDown World Model For Web Agents

2026-11-04 · Zhihao Nan, Sifan Zhou, Yiming Cheng, Jinkai Zheng, Zheng Zhu, Si Shi, Ming Li, Fei Yu

Research Track B · General AI

Graphical user interface (GUI) agents can improve decision-making with world-model foresight, provided that predicted states accurately reflect post-action interfaces. Existing state representations fail to jointly capture interface layout, UI semantics, and explicit locations. We introduce Typed Spatial Markdown (TSM)…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 9.4

From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence

2026-11-03 · Hao Fei

General AI

For a decade, progress in artificial intelligence has been measured by how much a machine can do on its own. Large foundation models now write code and run multistep tasks, and personal agents act on a person's behalf. Yet people still forget what they once knew, miss what they are not looking at, fail to find the righ…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.2

WeLM-Image: A Unified Image Generation Model towards Visual Intelligence

2026-11-05 · Canmiao Fu, Chen Li, Guohui Zhang, Hao Lu, Hongyang Wei, Huadong Wu, Huaisong Zhang, Hubery Yin, Liyuan Cui, Qixin Yan, Tong Shao, Xiaoqiang Zhou, Xinhang Leng, Ying Zhang, Zhenhai Liu, Zhipeng Huang

General AI

We present \textbf{WeLM-Image}, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and multi-reference synthesis. Designed for single-GPU deployment in WeChat's large-scale consumer applications, the model processes text, reference images…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.2

Where and Why is Grounded Reasoning Useful?

2026-11-05 · David Yan, Le Xue, Forrest Huang, Qiuyi Zhang, Dustin Tran, Andrew M. Dai, Yinfei Yang

General AI

Grounded reasoning, where a model outputs text coordinates of relevant locations in chain-of-thought reasoning, is a common strategy for solving complex visual reasoning problems. However, the benefits and limitations of grounded reasoning are understudied. We study where and why grounded reasoning is most useful. To d…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.4

LungMend: A Healthy-Only Latent Diffusion Shape Prior for Lung Mask Correction in Severe Tuberculosis CT

2026-11-04 · Rezkellah Noureddine Khiat, Pierre-Yves Brillet, Catalin Fetita

Research Track A · General AI

Lung segmentation models such as R231 are widely used, but they fail on severe tuberculosis (TB) CT: cavities and consolidations look like non-lung tissue and are left out of the mask. We present LungMend, a post-processing model that corrects such masks using only healthy anatomy. A latent diffusion model, trained on …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.4

When Less is More: Emerging Network-Wide Use Cases for Hollow-Core Fibers in Optical Networks [Invited]

2026-11-05 · Mëmëdhe Ibrahimi, Giovanni Simone Sticca, Angelo Ferrara, Francesco Musumeci, Massimo Tornatore

Research Track A

Hollow-Core Fiber (HCF) is emerging as a disruptive technology for next-generation optical networks, offering 30\% lower propagation latency than standard Single-Mode Fiber (SMF), record-low attenuation (0.05-0.1 dB/km), and nonlinearities reduced by three to four orders of magnitude. While the physical-layer benefits …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.2

A Multimodal Haptic Interface for Simultaneous Softness and Thermal Modulation

2026-11-05 · Joshua Brown, Fernando Bello, Lynette Jones

General AI

Haptic interactions, such as touching an object in virtual reality, involve detecting a plethora of sensations through the skin. Whilst tactile displays exist to simulate and manipulate all of these cues individually, little progress has been made constructing devices that can control multiple cues simultaneously. This…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.2

Do You Miss the Nights We Spent Crafting Figures? Rethinking Teaser and Framework Figures in the Age of Generative AI

2026-11-05 · Xiaoqi Zhao, Youwei Pang, Kailai Zhou

General AI

Scientific figures give research ideas a visual form through choices of abstraction, composition, and emphasis. Generative AI offers new ways to realize these choices, raising questions about explanatory clarity and purposeful visual expression. We examine these questions through a visual retrospective of 371 motivatio…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.2

FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning

2026-11-05 · Ali Mohammadi Ruzbahani, Abbas Yazdinejad, Hadis Karimipour

General AI

Federated learning servers combine client models with a fixed aggregation rule, and each rule in common use is designed for one kind of heterogeneity. We study whether a large language model (LLM) that inspects the client models can choose the rule itself, without any training on the server. In FedReason, the LLM is ca…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.2

ReproBridge: Building Reproducibility into ML Research Artifacts

2026-11-05 · Yubo Wang, Rui Meng, Jaehyun Nam, Tomas Pfister, Jinsung Yoon

General AI

Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts. For coding agents, reproduction success can therefore depend on their ability to fill in missing details, rather than on the released artifacts alone. We ask whe…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.2

The Geometry of Simulated Perspectives: Dissociating Representation and Behaviour in a Multimodal Language Model

2026-11-05 · Mathis Immertreu, Fitim Abdullahu, Thomas Kinfe, Claus Metzner, Helmut Grabner, Patrick Krauss, Achim Schilling

General AI

Multimodal language models can simulate different observers, yet it remains unclear how assigned perspectives reshape their internal representations and whether these changes govern their judgements. Here, we investigate the representational geometry of persona-conditioned visual interestingness in Qwen3-VL-8B-Instruct…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.2

VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding

2026-11-05 · Yu-Cheng Chou, Shihao Wang, Jin Huang, Chi-Pin Huang, Chiao-An Yang, Xianzhe Fan, Jing Wang, Zhiqi Li, Yuanguo Kuang, Ruijie Zheng, Johan Bjorck, Sifei Liu, Hang Su, Abhishek Badki, Lei Zhang, Alan Yuille, Linxi "Jim'' Fan, Jan Kautz, Zhiding Yu

General AI

Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to represent spatial goals and anticipate motion. However, autoregressive vision-language models generate these plans one coordinate token at a …

Review
pending
Role
unreviewed
Read
soon
huggingface Score 7.4

StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models

2026-11-03 · Chenru Wang, Xuanyang Zhang, Yucheng Han, Wenbo Nie, Wei Cheng, Xianfang Zeng, Gang YU, Chi Zhang

General AI

A deployable text-to-image diffusion model must hold several capabilities at once, such as instruction following, text rendering and human preference, and must sample in a few steps. Capabilities and few-step sampling are built in separate stages: a full-step model first consolidates capabilities through multi-teacher …

Review
pending
Role
unreviewed
Read
soon
huggingface Score 7.4

On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer

2026-11-04 · Zhenyi Shen, Junru Lu, Wei Liu, Jiangnan Ye, Jiazheng Li, Di Yin, Xing Sun, Tameem Adel, Yali Du, Lin Gui, Yulan He

General AI

Prefill-to-Autoregressive Cross-model Transfer (PACT), a form of latent communication between language models, combines a larger model's prompt representations with a smaller model's efficient generation, offering a promising way to balance capability and inference cost. However, existing systems provide limited suppor…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 7.4

Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation

2026-11-04 · Georgios Feretzakis, Alexandros Papaspyridis

General AI

Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text and precomputed embedding vectors. A signature proves who published a pack, not that its vectors encode its text. We study this text-vector integrity gap. A verifier that recomputes vectors and accepts…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 7.4

Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation

2026-11-05 · Kotaro Oishi, Kazuma Ikeda, Ryosei Hara, Ryo Yoshida, Mariko Isogawa, Kentaro Yoshioka

General AI

LiDAR is a critical sensor for autonomous driving and robotics, yet it remains vulnerable to adverse conditions such as fog, rain, transparent objects, and low-reflectance surfaces. Full-waveform LiDAR (FWL) addresses these limitations by capturing the complete return waveform as a histogram, preserving rich reflection…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.2

Acoustic Anomaly Detection for Early Identification of Drill Jamming

2026-11-05 · Maria Beatriz Silva, Lucas Edson Silva de Araújo, Sergio F. Chevtchenko, Ermeson Andrade, Danilo Araujo, Saeed Afshar

General AI

In the context of Industry 4.0, predictive maintenance is essential to minimize unplanned downtime and ensure operational safety. In machining processes, drill jamming is a critical failure that compromises both workpiece quality and tool integrity. This work proposes an acoustic anomaly detection system using ultrason…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.2

Cognitive Tours: Making Understanding a Deliverable in AI-Assisted Development

2026-11-05 · Margaret-Anne Storey

General AI

Generative AI and agentic coding are accelerating software development, leading to concerns about technical debt. But two less visible forms of debt, cognitive debt and intent debt, are emerging as key risks to software health. Cognitive debt is the absence or erosion of a team's shared understanding where no one can c…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.2

Souffleur: A Glanceable Display for Mobile Voice Conversations

2026-11-05 · Anton Wolter, William Benjamin, Niklas Elmqvist

General AI

The speech capabilities of mobile devices have grown, but their displays still rely on a text-based chat. When resuming a voice chat after a context switch, the last messages may not convey the key points of the conversation. Autobiographical use and sessions with external participants led to design goals for a mobile-…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.2

User Embeddings are Superpositions of Interpretable Behavioral Modes

2026-11-05 · Jonathan Kozaczuk, Zheng Dong, Noyan Evirgen, Keivan Majidi, Eddie K. H. Ng, Chris Porter, Qi Zhao, Jia Geng, Changmao Li, Brandon R. Feng

General AI

User embeddings are central components of modern recommendation, personalization, and behavioral modeling systems. Though these embeddings can compactly encode rich behavioral information, they are inherently dense and opaque, limiting interpretability. To address this gap, we argue that user embeddings can be understo…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 7.0

HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation

2026-11-02 · Gyeonghun Kim, Donghoon Kim, Minsoo Choi, Suyun Lee

General AI

Recent advances in Vision-Language-Action (VLA) models have enabled fine manipulation capabilities, yet performing tasks that require working memory remains a key challenge. Most existing VLA architectures operate under a Markovian assumption, mapping only the current observation to an action, which leads to failure in…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.2

Align Before Aggregation: Basis-Consistent Federated LoRA under Heterogeneous Ranks

2026-11-05 · Pengpeng Qiao, Yang Cao, Lingling Zhang, Guo Cheng, Junwei Chen, Manjiang Yu, Wei Yang Bryan Lim, Masatoshi Yoshikawa

General AI

Federated fine-tuning of large language models (LLMs) under heterogeneous client capacities is increasingly important, and low-rank adaptation (LoRA) with heterogeneous ranks makes it practical. Existing server-side aggregators compose local matrix updates $ΔW_i$ from client-specific LoRA factors $(A_i,B_i)$ before agg…

Review
pending
Role
unreviewed
Read
later
arxiv Score 6.2

Scientist World: Grow a Research World for AI-Scientists

2026-11-05 · Taiming Lu, Sachin Konan, Zhuang Liu

General AI

AI-Scientists arrived, but a world for them to grow in did not. Human scientists take theirs for granted $-$ centuries of open problems and shared ideas, waiting in the scientific literature. To AI-Scientists, that world is readable but not runnable, so we build Scientist World for them: every research paper becomes an…

Review
pending
Role
unreviewed
Read
later
arxiv Score 6.2

SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization

2026-11-05 · Qile Jiang, George Em Karniadakis

General AI

LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation …

Review
pending
Role
unreviewed
Read
later
arxiv Score 6.2

Unpacking the Compute Efficiency of Strong-to-Weak OPD against GRPO

2026-11-05 · Zeyu Leo Liu, Yang Li, Bo Pang, Emre Can Acikgoz, Xuan-Phi Nguyen, Anurag Koul, Srijan Bansal, Erik Nijkamp, Shafiq Joty, Semih Yavuz

General AI

On-policy distillation (OPD) trains a student on its own rollouts under a frozen teacher's per-token supervision. Does this dense signal reduce the training FLOPs needed to reach a target accuracy compared with reinforcement learning? We systematically compare vanilla reverse-KL OPD with Group Relative Policy Optimizat…

Review
pending
Role
unreviewed
Read
later
huggingface Score 5.4

TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing

2026-11-04 · Ruikang Li, Zixuan Chen, Jiarui Wu, Mingde Yao, Yiyuan Zhang, Yujin Wang, Hanming Deng, Lewei Lu, Tianfan Xue

General AI

Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift. This long-term drift is often mitigated through training on multi-turn data or cross-turn rollouts, potentially altering p…

Review
pending
Role
unreviewed
Read
later
arxiv Score 5.2

Latent RL Priors for Data-Efficient Dexterous Manipulation

2026-11-05 · Yixiao Wang, Peiyi Chen, Mustafa Mukadam, Shreekant Gayaka, Masayoshi Tomizuka, Son Tran

General AI

Learning dexterous manipulation from limited visual demonstrations is challenging because policies must acquire both perceptual grounding and precise control, while reinforcement learning (RL) in simulation can acquire rich control behaviors from large-scale interaction with privileged information. We introduce \textbf…

Review
pending
Role
unreviewed
Read
later
huggingface Score 5.0

SynthFaces: Balanced Large Scale Human Dataset

2026-10-29 · Sergey Karpukhin, Denis Bobkov, Kirill Morozov, Aibek Alanov

General AI

The pursuit of fair and equitable AI in human-centric tasks is critically hindered by the inherent biases and privacy risks of real-world datasets, which offer imbalanced representations of identity and often contain sensitive personal information. Consequently, state-of-the-art generative models trained on this skewed…

Review
pending
Role
unreviewed
Read
later
huggingface Score 5.0

Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition

2026-10-30 · Tahar Chettaoui, Guray Ozgur, Eduarda Caldeira, Naser Damer, Fadi Boutros

General AI

Multi-head attention in Vision Transformers (ViTs) allows independent attention patterns across heads, but without explicit regularization, heads may learn redundant patterns rather than complementary roles. Correlation-based penalties encourage head disentanglement, yet apply uniform regularization across all training…

Review
pending
Role
unreviewed
Read
later