Research Paper Cockpit

Daily Digest - 2026-11-11

Papers first seen in this daily snapshot.

Daily Archives

Quick jump into generated daily digests.

Research Workflow

Latest digest: 2026-11-17.

Papers

57 visible entries

arxiv Score 28.5

A Margin Perspective on LoRA: Robustness to Catastrophic Forgetting and Adapter Merging (MaLoRA)

2026-11-10 · Ziqing Xu, Hancheng Min, Lachlan Ewen MacDonald, Salma Tarmoun, Enrique Mallada, Weijie Su, Rene Vidal

Research Track A

Low-rank adaptation (LoRA) is the de facto method for parameter-efficient fine-tuning of large neural networks, achieving strong task adaptation with minimal trainable parameters and low optimization cost. Beyond this efficiency, practitioners have observed two striking properties: \textit{robustness to catastrophic fo…

Review
pending
Role
unreviewed
Read
now
arxiv Score 23.5

Unipolar Neuron Networks Trained by Recirculation for Reward-Based Continual Learning

2026-11-10 · Florin Leon

Research Track A

Unipolar neurons are the predominant type of nerve cell in the octopus and in most other invertebrates. A single neurite (a fiber extending from the cell body) branches into a tree that carries both input and output synapses. The branches send graded local outputs to nearby cells, and one site on the main neurite sends…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.9

Autonomous Continual Learning and Knowledge Transfer via Cortex-Inspired Neural Assemblies

2026-11-09 · Kevin L. McKee

Research Track A

Unlike the brain, artificial neural networks (ANNs) suffer from "catastrophic forgetting": complete overwriting of solutions when re-training on new functions ("concept shift") or on a disjoint domain of the current function ("domain shift"). ANNs require each batch of data to be roughly representative of the complete …

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.5

Continual-ARC: Measuring Skill Acquisition over a Working Lifetime

2026-11-10 · Daniel Lenton, Yusha Arif, Haris Mahmood

Research Track A · General AI

Agent harnesses have emerged as a promising mechanism for continual learning, alongside test-time parametric learning. However, the current benchmarks have several limitations: they generally focus on a single applied domain, serve each instance only once, and assume a single family of learner, so memory-based and weig…

Review
pending
Role
unreviewed
Read
now
huggingface Score 20.4

Micius-Flash: Lightweight Agentic Intelligence for Engineering

2026-11-04 · Hongcheng Gao, Weiheng Li, Yipeng Wei, Yu Lei, Shuo Sun, Yi Li, Yajiao Wang, Jie Luo, Jianwei Wen, Xinyi Zhou, Hongda Li, Yibing Zhang, Henghui Sun, Yufan Zhou, Tianfang Hao, Naihao Xue, Hailong Qu, Jingjing Zhou, Peng Xu, Yongzheng Wei, Yichen Zhu, Ziying Wang, Yibo Wang, Jianshu Zeng, Yuhang Lei, Zeqiang Wang

General AI

We introduce Micius-Flash, a 27-billion-parameter model for engineering with native multimodal input, deep reasoning and a 256K-token context window. We design the Micius data pipeline as a knowledge-tree-driven data flywheel comprising three stages: knowledge tree construction and expansion, data synthesis, and qualit…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.8

Hx2Dx: From Anamnesis to Diagnosis - A Multimodal Arena for Conversational Clinical Reasoning in LLMs

2026-11-10 · Federico Ravenda, Mirko Cesarini, Daniele Montagnani, Volodymyr Karpenko, Antonietta Mira, Andrea Raballo

General AI

Large language models (LLMs) achieve expert-level diagnostic accuracy in static evaluations, where the model receives a curated vignette or case report that already condenses the diagnostically relevant findings. Such evaluations measure inference over already selected evidence; the evaluations do not account for the i…

Review
pending
Role
unreviewed
Read
now
huggingface Score 19.0

MMDM: Measuring Massive Multitask Decision Making

2026-11-10 · Junhao Shen, Qing Zong, Yue Guo, Zhanqiu Zhang, Yiwen Guo, Hong Cheng

General AI

System-1 Decision Models directly make structured probabilistic decisions over query-specified options given a state in a single forward pass, without autoregressively generating reasoning trajectories or textual responses. Recent evaluations cover diverse tasks but often rely on existing benchmarks, where prior exposu…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.8

Chain of Physics: Supporting Fault Diagnosis with Engineering-Inspired Large Language Model Reasoning

2026-11-10 · Wenqi Zhou, Leonardo Baldo, Kai Goebel, Manuel Arias Chao

General AI

Fault diagnosis in complex systems requires linking observed changes in physical quantities to the failure mechanisms that produce them. Experienced engineers perform this task by combining sensor information with knowledge of system behavior and fault propagation. Large Language Models (LLMs) can support this process,…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.8

Evaluating LLM-Generated World Models for Neuro-Symbolic Reasoning

2026-11-10 · Souhaila Djaffal, Amna Jamal, Gagana Madhugiri Devaraja, Anidipta Pal, Jobst Heitzig

General AI

Formal world models can support planning, verification, and safety reasoning, but constructing them from open-ended natural-language situations is difficult, particularly in multi-agent settings where several formalizations may be plausible. We study whether five LLMs can generate such world models as partially observa…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.5

When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents

2026-11-10 · Runxuan Tang, Haoyu Gao, Yuyan Ding, Junyi Yao, Zihao Zheng, Zecheng Sheng, Liwei Hou

Research Track B · General AI

LLM agents increasingly operate in long-horizon, verifier-rich environments, but current self-improvement mechanisms often write episode-derived lessons directly into memory, making local success an unreliable signal for reusable and safe knowledge. This paper addresses the core question of when an experience-derived b…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.8

A Cross-Scenario Survey and Analysis of Self-Evolving Multimodal Agents

2026-11-10 · Jingjing Jiang

Research Track A · General AI

Recent work shows that multimodal agents increasingly self-improve without recurring human annotation. However, each self-improvement mechanism is designed and evaluated within a single scenario, leaving its preconditions unverified under cross-scenario transfer. This survey investigates the structural source of asymme…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.8

Cognitive Mapping of Learning by Thinking Mechanisms in Large Language Models

2026-11-10 · Dong Han, Jin Zhang, Kunyue Yang

General AI

Large language models (LLMs) increasingly exhibit capabilities that resemble human Learning by Thinking (LbT), the acquisition of new insight through internal processes such as explanation and reasoning, without new external input. A systematic account of the cognitive mechanisms behind these capabilities, and of their…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.9

Anchor Behavior, Not Parameters: Rehearsal-Free Continual Learning with a Single Shared Prompt

2026-11-09 · Duy-Cuong Bui, Trung-Anh Dang, Vincent Nguyen, Duc V. Le, Ngoc-Son Vu

Research Track A · General AI

Prompt-based continual learning adapts a frozen pre-trained vision transformer by tuning a small set of prompt tokens. Recently, one-prompt methods which share one single prompt across all tasks make this paradigm maximally parameter efficient. The open question is how a shared prompt can keep the knowledge of old clas…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.8

PARLEY: Evaluating LLM Collaboration Through Cooperative Asymmetric Puzzles

2026-11-10 · Javier Hernandez, Andrew D. Wilson

General AI

As large language models power autonomous agents, understanding how they collaborate and where they fail becomes critical. We introduce PARLEY, an extensible platform for studying LLM agent collaboration through four asymmetric puzzle tasks grounded in cognitive psychology (referential communication, joint coordination…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.8

Persistent Metric-Semantic Maritime Scene Memory from Open-Vocabulary 3D Scene Graphs

2026-11-10 · Kim Alexander Christensen, Dina Zimmermann, Martin Steinert, Eleni Kelasidi

Research Track A · General AI

Three-dimensional scene graphs (3DSGs) can provide robots with persistent metric-semantic representations for spatial reasoning, but the existing methods have primarily been developed for indoor and terrestrial environments. In this paper we investigate how a representative outdoor open-vocabulary method transfers to m…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.8

Pyrite: Building and Benchmarking Protein-Ligand Pose Ranking Agents

2026-11-10 · Megha Srivastava, Michael H. Lim, Allison M. Keys, Pranav Murugan, Nate Gruver

General AI

Predicting how a ligand binds to its target is central to small-molecule drug discovery. Modern cofolding models can generate diverse candidate poses, but reliably ranking these candidates remains challenging. We introduce Pyrite, a pairwise pose-ranking benchmark comprising 1,500 pose pairs across diverse protein-liga…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.8

ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows

2026-11-10 · Kaiyuan Hou, Yang Ping Kuo, Indranil Bhattacharya, Rohith Nama, Arushi Gupta, Carlos D. Castillo, Prathap Ramachandra, Xiaofan Jiang, Francesco Carbone

General AI

Business process automation runs the same Standard Operating Procedure (SOP) again and again on new inputs. Large Language Model (LLM) agents can follow an SOP written in natural language, but they call an LLM to choose every step of every run, which adds latency and cost at scale. We present ReTrace, which turns an SO…

Review
pending
Role
unreviewed
Read
now
huggingface Score 15.4

EarthRecord: From Pixels to Land Change with Multimodal Agents over Four Decades of Satellite Imagery

2026-11-06 · Haoran Zhang, Huizhen Sun, Hanbin Wen, Jie Leng, Jiaxin Zhu, Zhaohua Sun

General AI

While multimodal agents now carry out complex data analysis with tools, their ability to turn decades of satellite imagery into reliable land-change analysis, crucial for Earth observation science, remains unmeasured. Existing benchmarks fall short: they pose questions on curated images or give agents preprocessed inpu…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.2

Harness Matters: Measuring and Dissecting Security Resilience in Web Agents

2026-11-09 · Xinyi Wu, Jiagui Chen, JiaYi Dong, Geng Hong, Xudong Pan, Jiarun Dai, Mingxuan Liu, Min Yang

Research Track B · General AI

Web agents extend LLMs from text generation to real-world web interaction by relying on execution harnesses that interpret user goals, perceive webpages, plan actions, and ground model decisions into browser operations. While prior work has recognized that agent security depends on more than the backend model alone, ho…

Review
pending
Role
unreviewed
Read
now
huggingface Score 14.5

Tree-Ising: Repairing Language Models with Bit-Level Ising Edits

2026-11-10 · Hadi Salloum, Ammar Ali

General AI

Weight-space programming, introduced in recent MIT work by Takehi et al., enables a frontier LLM agent to read a network's weights and write a repair. Their GPT-6 Astra agent corrected the reasoning loops of Qwen3.5-0.8B without gradients, using 158 agent turns, 89.7 million tokens, and 50 forward-pass requests. Our me…

Review
pending
Role
unreviewed
Read
now
huggingface Score 14.4

FINCOSMOS: An Open-World Evaluation Paradigm for Agents in Finance

2026-11-05 · Yupeng Cao, Xueqing Peng, Lingfei Qian, Haohang Li, Yangyang Yu, Anke Xu, Wenbo Cao, Yan Wang, Yuechen Jiang, Yuyan Wang, Zhuohan Xie, Yankai Chen, Zehan Li, Jimin Huang, Xue Liu, Jian-Yun Nie, Sophia Ananiadou

General AI

Language agents increasingly work for users on the open Web, and finance is where trusting them is hardest. The data must come from the Web, the strategy lives in the user's head, and correctness depends on time, so an agent can fail silently: a strategy the user never asked for, unverified data, or a backtest that use…

Review
pending
Role
unreviewed
Read
now
huggingface Score 13.9

The Surprising Effectiveness of Deleting Weights in LLM Post-Training

2026-11-07 · Jack Lu, Zhenbang Yang, Mike Lasby, Tejas Pote, Yani Ioannou, Mengye Ren

Research Track A · General AI

How little of a pretrained large language model (LLM) has to change for it to acquire new capabilities? We find that zeroing fewer than 0.05% of its weights, with no other modification, matches full fine-tuning (FFT) at scale across three LLM post-training regimes: reinforcement learning with verifiable rewards, superv…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.4

VLA-MOPD: On-Policy Distillation for Multi-Task VLA Policy Consolidation

2026-11-09 · Yongxuan Lv, Zhen Fang, Lichen Man, Hao Li, Pu Li, Hengyi Wang, Langfeng Cao, Lin Chen, Jie Huang, Xiu Su, Shan You, Fei Wang, Feng Zhao

Research Track A · General AI

Physical intelligence requires embodied agents to ground language in observations and execute actions while retaining useful skills. Vision-language-action (VLA) policies offer a shared interface, but task-specific post-training often produces separate specialists. Consolidation is difficult: mixed-task reinforcement l…

Review
pending
Role
unreviewed
Read
now
huggingface Score 13.0

Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents

2026-11-10 · Yukyeong Lee, Yumin Choi, Jinheon Baek, Sung Ju Hwang

General AI

External memory enables LLM agents to improve from experience by distilling trajectories of past tasks into concise lessons for new tasks. However, memory can also lead to memory-induced degradation, where an agent fails on tasks it would solve without memory, often because it follows a lesson that is incorrect, or mis…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.0

Personalized Affective Perception via Continual Learning in Human-Agent Negotiation

2026-11-10 · Mehmet Onur Keskin, Berk Buzcu, Nikhil Churamani, Reyhan Aydogan, Hatice Gunes, Catholijn Jonker

Research Track A · General AI

Self-interested intelligent agents that negotiate with humans should interpret nonverbal expressions and adapt their behavior accordingly. However, generic facial-affect models degrade across individuals and contexts, creating a generalization gap. We introduce an affect-adaptive negotiation strategy that incorporates …

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.8

AutoScaffold: AI-Guided Scaffolding for Reinforcement Learning of Language Models

2026-11-10 · Zijian Zhang, Rizhen Hu, Jiangweizhi Peng, Shiyang Li, Sujay Bhatt, Sihan Zeng, Mingyi Hong

General AI

Reinforcement learning with verifiable rewards (RLVR) produces rich training experience, yet outcome rewards reduce each attempt to a single number and leave most of this information unused. Training-time scaffolds, such as strategies or hints added to the prompt during training, offer a natural way to turn this inform…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.5

MEOW: Medical Open-World Interactive Segmentation

2026-11-10 · Philip Matthias Winter, Maria Wimmer, Bernhard Schäfl, David Major, Dimitrios Lenis, Astrid Berg, Theresa Neubauer, Ariharasudhan Muthusami, Johannes Novotny, Georg Zotti, Katja Bühler

Research Track A · General AI

In open-world recognition, machine learning models not only make predictions on unknown structures ("generalized open-set"), but also continually learn and improve from those predictions over time. Interactive segmentation, despite its access to user feedback, has so far remained confined to the open-set setting. In th…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.8

LM-SimBench: A Unified Framework, Dataset, and Benchmark for Large Language Model Training Simulation

2026-11-10 · Yu Dong, Hong Li, Qiang Sun, Xu Zhou, Jinbiao Huo, Qixiu Cheng, Zhiyuan Liu

General AI

Evaluating candidate parallelization strategies through distributed training runs makes strategy selection prohibitively expensive at scale. Performance simulation offers a lower cost alternative, yet controlled comparisons among existing simulators remain difficult because they differ in the training stages they model…

Review
pending
Role
unreviewed
Read
now
arxiv Score 11.8

One Policy for 100 Household Tasks: Our Solution for the 2026 BEHAVIOR Challenge

2026-11-10 · Ilia Larchenko, Gleb Zarin, Atindra Nair, Keerti Manney, Vitaly Kleban, Mirko Kiefer, Anjana Yodaiken

General AI

We describe our solution for the 2026 BEHAVIOR Challenge: 100 long-horizon household tasks in the OmniGibson simulator. We placed 9th on the final leaderboard, the only independent team in the top 10. The core of the solution is a single vision-language-action (VLA) model, one checkpoint for all 100 tasks, built on our…

Review
pending
Role
unreviewed
Read
now
huggingface Score 10.9

Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists

2026-11-09 · Guowei Xu, Jiaru Zou, Mete Erdogan, Haotian Ye, Pan Lu, James Zou

Research Track A

Scientific discovery requires ideas that are original, useful, and non-obvious. Yet AI scientists are typically given as much task information as possible during idea generation, which can anchor generation toward familiar approaches. Inspired by the cognitive framework of Blind Variation and Selective Retention (BVSR)…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.8

Alania-2: Turkish text-to-speech with instant and fine-tuned voice cloning

2026-11-10 · Sezgin Saygili, Emre Kaplaner, Oncel Ozgul, Fikri San Koktas

General AI

We present Alania-2, a Turkish text-to-speech (TTS) system with two built-in voices, voice design from text descriptions, and two kinds of voice cloning. Alania-2 is a 488M-parameter model with the VoxCPM architecture, which generates continuous audio latents with a diffusion head on top of a language-model backbone. W…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.8

Can AI be a 'Researcher Without Borders'? Auditing Bias in AI-Assisted Social Science Research about China and the US

2026-11-10 · Yuan Zhang, Thales Bertaglia, Ralph Schroeder

General AI

Although large language models have demonstrated strong performance on algorithmic and mathematical tasks, their suitability as social science research assistants remains unclear, particularly because many social science questions lack agreed-upon, quantifiable benchmark answers. Evaluating this suitability is importan…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.8

Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents

2026-11-10 · Howard Zhang, Chuck Arvin, Logan Brown, Mihir Bhatia, Neelu Choudhary, Lily Miao

General AI

Deploying LLM-based analytics agents in enterprise settings requires evaluation frameworks that can reliably detect failures across complex, multi-tool workflows. We present a three-phase comparative study of three evaluation frameworks, each representing a distinct evaluation paradigm (trace-based LLM judging, text-on…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.8

Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations

2026-11-10 · Ziang Liu, James J. Kim, Yijia Dai, Jennifer J. Sun

General AI

LLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most of them evaluate hypotheses pointwise, testing an empirical claim $h$ only against its complement $\neg h$. When evidence rejects $h$, the agent learns that one explanation is unlikely but not which alternative the evidence supp…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.8

TAMEing the Open-World Personalization: Towards Open-Set Personalized MLLM Assistant

2026-11-10 · Rongpei Hong, Jian Lang, Ting Zhong, Fan Zhou

General AI

Personalizing Multimodal Large Language Models (MLLMs) as intelligent assistants has recently emerged as an active research topic, where an MLLM is expected to go beyond generic, one-size-fits-all replies, and instead generate responses grounded in user-specific objects, entities, and concepts encountered during intera…

Review
pending
Role
unreviewed
Read
now
arxiv Score 10.2

Suppression Is Not Erasure: Mechanistic Analysis and Reactivation Boundaries of Subspace Projection for LoRA Backdoor Defense

2026-11-09 · Junsheng Fu, Shuangshuang Gao

General AI

Low-Rank Adaptation (LoRA) is the standard paradigm for customizing large language models, yet third-party LoRA adapters pose a supply-chain risk: modifying less than 1% of model parameters suffices to implant stealthy backdoors. Recent defenses project adapter weights onto estimated backdoor subspaces, reporting near-…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.9

Latin American Studies since the 1980s: From Apocalyptic Dreams to Assimilationist Consolidation

2026-11-09 · Thiago Dumont Oliveira, Juan Grigera, Pedro Mendes Loureiro

Research Track A

We investigate how Latin American Studies (LAS) has evolved since 1982 in three leading LAS journals. Using network analysis, text mining, and bibliometrics, we trace transformations in disciplinary positioning, authorship, and citation patterns. Our main claim is that LAS has undergone an assimilationist consolidation…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.8

AI Isn't Getting Dumber, We're Getting Pickier: Rising Standards in Human Evaluation of Large Language Models

2026-11-10 · Zihan Chen, Lei Nico Zheng, Di Zhu

General AI

Users often complain that AI assistants such as ChatGPT are getting worse. Some versions do change, but human evaluation leaves a second possibility untested: the people judging may change. We separate the two on Chatbot Arena, a public platform where people compare answers from two anonymous large language models (LLM…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 9.4

Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning

2026-11-09 · Xinjie Shen

General AI

Reinforcement learning (RL) can improve an agent's task capability while reinforcing behavior that violates contextual execution requirements. We study this reward-driven misalignment, including reward hacking, through verifiable reward--context conflicts, where compliant task completion remains feasible while some exe…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.8

Emergent Biological Capabilities in a Foundation Model for Molecular Interactions

2026-11-10 · Adi Mashiach

General AI

Foundation models trained on large unlabeled corpora develop emergent capabilities, tasks that go beyond the training objective. We extend this paradigm to multimodal biology with Bonbon, a foundation model for molecular interactions trained on approximately 3.2 trillion tokens of paired protein-ligand sequences. From …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.8

GARD: Gradient-Guided Adversarial Representation Defense against Backdoors in Multimodal Contrastive Learning Models

2026-11-10 · Yuhong Wang, Yujun Cai, Lei Feng, Songze Li

General AI

Multimodal contrastive learning models such as CLIP are vulnerable to backdoor attacks with diverse trigger structures, ranging from localized patches to globally distributed perturbations, with recent attacks increasingly optimizing these triggers in the representation space. Existing post-hoc defenses based on clean …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.8

Multimodal Abstention That Preserves Acquired Correct Answers

2026-11-10 · Jinyuan Zhang

General AI

Adding abstention to a task-adapted multimodal model can discard correct answers, including capabilities acquired during adaptation. We formulate abstention repair as maximizing correct abstention on unanswerable questions under a budget on newly lost correct answers. We propose ReFrain (Regression-Free Abstention), wh…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 8.4

MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations

2026-11-07 · Lorenz K. Muller, Philippe Bich, Chiara Boretti, Hyun-Min Chang, Jiawei Zhuang, Lukas Cavigelli

General AI

Weight-activation quantization can reduce the memory and compute cost of neural-network inference, but recent methods often require expensive optimization and architecture-specific propagation of basis transforms across layers. We introduce MACaQ, an MXFP4 W4A4 post-training quantization method that treats every linear…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.4

OCEAN: A Five-Phase Framework for Meaningful Change

2026-11-09 · A. Fronzetti Colladon

Research Track A

Managing meaningful change requires more than motivation, insight, or isolated techniques. This paper introduces OCEAN, a five-phase conceptual framework for structuring nonclinical developmental conversations and change-oriented work in coaching and in the practice of leaders and HR professionals. The five phases are …

Review
pending
Role
unreviewed
Read
soon
huggingface Score 8.4

WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning

2026-11-09 · Sang-Hoon Lee, Ha-Yeong Choi

General AI

This work proposes WaveGen, a fully end-to-end diffusion-based text-to-waveform framework based on Spectral Forcing, which jointly learns an internal spectral trajectory and the target waveform trajectory within a single model, enabling direct end-to-end text-to-waveform generation. Unlike recent TTS pipelines, WaveGen…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 8.0

Lipschitz-Controlled Flow Matching for Robust Image Restoration

2026-11-10 · Sedjro Salomon Hotegni, Konstantin Sonntag, Paul-Christian Bürkner, Sebastian Peitz

General AI

Flow-matching models can produce high-quality image restorations, but their learned dynamics may amplify small input perturbations and make reconstructions unstable. We introduce LipsFlower to reduce this amplification. We derive stability bounds for Flow-from-Y, which initializes the ordinary differential equation fro…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 7.0

Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models

2026-11-10 · Tomer Solberg

General AI

We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with no floating-point step, in which every rounding, normalization, softmax and sampling dec…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.8

Gaussian Process-Augmented Model Predictive Contouring Control for 6-DoF Trajectory Tracking with a Holonomic AUV

2026-11-10 · David Dörner, Giancarlo Troni, Ignacio Torroba, Ivan Stenius

General AI

Small, holonomic Autonomous Underwater Vehicles (AUVs) enable close-range inspection of underwater structures from arbitrary viewpoints, requiring accurate position and attitude tracking under state and input constraints. Model Predictive Contouring Control (MPCC) naturally handles these requirements, but relies on an …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.8

Medical Image Segmentation: Foundation Model Adaptation versus Task-Specific Training

2026-11-10 · Emre Kutlusan, Yongmin Li

General AI

Foundation models pretrained on large natural-image collections are increasingly adapted for medical image segmentation, in the expectation that they will replace models trained for each task. Most comparisons, however, use data from the training distribution and a single task-specific baseline whose configuration is r…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.8

TanCRAFT: Context-Reasoned Anticipatory Feedback for Assembly Tasks

2026-11-10 · Sassan Mokhtar, Lars Doorenbos, Marius Bock, Sina Mokhtar, Katharina Beckh, Dominik Bach, Juergen Gall

General AI

Preventing human error in physical assembly tasks requires assistance systems that can intervene before mistakes are made. This is especially challenging in settings where users are free to choose the construction order and correctness depends on the evolving assembly rather than a fixed next step. We present TanCRAFT,…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.8

What Factors Matter for Collection-Level Counting with Human-AI Collaboration?

2026-11-10 · Seoyun Jeong, Logan Lawrence, Owen L. Martin, Benjamin Koger, Daniel Sheldon, Subhransu Maji

General AI

Many scientific and policy decisions require estimating the total number of target objects across a large image collection. Exhaustive human labeling is often infeasible, while raw model predictions can be biased, especially under domain shift. Recent human-AI estimation methods combine imperfect model predictions with…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 6.2

Stochastic Projections and Rank-Aware Learning Rates for Federated LoRA

2026-11-09 · Saber Malekmohammadi, Kevin Kuo, Virginia Smith, Golnoosh Farnadi

General AI

Fine-tuning large-scale foundation models across resource-constrained, distributed clients presents significant computational and communication challenges. While merging Low-Rank Adaptation (LoRA) with Federated Learning (FL) enables rank-based flexibility, the interdependence of the adaptation matrices ($\mathbf{A}$ a…

Review
pending
Role
unreviewed
Read
later
huggingface Score 6.0

From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents

2026-11-01 · Xingyu Yi, Xinya Zhang, Yunshen Zhou, Haoyu Bao

General AI

A scientific agent can give the same verdict while reading and citing different evidence. BioAgent-DF tests this separation using paired reference and candidate values saved at the same scientific computation site. It restores or transplants those values at their original coordinates, then runs the agent on healthy har…

Review
pending
Role
unreviewed
Read
later
arxiv Score 5.8

Demonstration of MANA: Multi-perspective Alignment of NPC Agents

2026-11-10 · Amir Tahmasbi, Keshav Singh, Shaheer Raza, Owen Mei, Jason Wu

General AI

We present MANA (Multi-perspective Alignment of NPC Agents), an interactive approach for authoring NPC behavior through embodied demonstration. We show MANA in the context of Minecraft, where a developer aligns NPCs while playing the game itself. Activating MANA lets the developer dynamically switch into the point of v…

Review
pending
Role
unreviewed
Read
later
arxiv Score 5.8

Second-Best Trade Is Half Efficient in Multidimensional Markets

2026-11-10 · Dirk Bergemann, Yang Cai, Kangning Wang, Jinzhao Wu, Renzhe Xu

General AI

We prove that at least half of the first-best gains from trade can always be achieved in multidimensional two-sided markets with additive values and costs and arbitrary downward-closed feasibility constraints. The guarantee is achieved by a mechanism satisfying Bayesian incentive compatibility, interim individual ratio…

Review
pending
Role
unreviewed
Read
later
arxiv Score 5.8

SinkState: On-the-Fly SVD of Recurrent States for Efficient Hybrid LLM Serving

2026-11-10 · Haolin Jiang, Weihang Li, Zhongzhu Zhou, Jinwen Pan, Santosh Pandey, Hang Liu

General AI

Hybrid models combine softmax attention with linear attention, which compresses history into fixed-size recurrent states to balance model quality and inference efficiency. However, linear attention has not pushed this compression to its limit: we find that the queries, keys, and values of linear layers concentrate in a…

Review
pending
Role
unreviewed
Read
later
arxiv Score 5.2

BridgeKV: Large-Model Prefill and Small-Model Decoding for LLM Inference via KV Cache Translation

2026-11-09 · Payman Behnam, Debopam Sanyal, Pranav Ponnusamy, Kusum Meda Ravi, Pranav Sastry, Mani Chandana Bandaru, Alind Khare, Myungjin Lee, Alexey Tumanov

General AI

LLM inference has two phases with different bottlenecks: LLM prefill runs once per request and is compute-intensive. Decoding repeats for every output token and is limited by memory bandwidth. To address the challenges associated with this issue, different solutions have been proposed. All of these solutions use the sa…

Review
pending
Role
unreviewed
Read
later