AI & Machine Learning · Fri, Nov 6, 2026

Machine learning, AI, natural language processing, computer vision and multi-agent systems.

RSS feed

Notable only (★4+)

arXiv cs.LGNov 6, 2026 #

User Embeddings are Superpositions of Interpretable Behavioral Modes

Explanation and summary in progress

Jonathan Kozaczuk, Zheng Dong, Noyan Evirgen et al.

arXiv cs.CVNov 6, 2026 #

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

Explanation and summary in progress

Xiaoqi Zhao, Youwei Pang, Kailai Zhou

arXiv cs.CVNov 6, 2026 #

Where and Why is Grounded Reasoning Useful?

Explanation and summary in progress

David Yan, Le Xue, Forrest Huang et al.

arXiv cs.AI · cs.NENov 6, 2026 #

SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization

Explanation and summary in progress

Qile Jiang, George Em Karniadakis

arXiv cs.AI · cs.CL · cs.LGNov 6, 2026 #

Scientist World: Grow a Research World for AI-Scientists

Explanation and summary in progress

Taiming Lu, Sachin Konan, Zhuang Liu

arXiv cs.CVNov 6, 2026 #

EgoGeneralist: Unifying Egocentric Action-Video Tasks through Video-Native Modeling

Explanation and summary in progress

Yanlin Jin, Bowen Yang, Cheng Zhang et al.

arXiv cs.LG · cs.AINov 6, 2026 #

XStack: A Benchmark for ML Repo Migration

Explanation and summary in progress

Linrong Cai, Taiming Lu, Haozhe Chen et al.

arXiv cs.LG · cs.AI · q-bio.NCNov 6, 2026 #

Same Behavior, Different Mechanism: What Finite Experiments Can Certify About Integrated Information

Explanation and summary in progress

Linqian Wu, Diaoxuan He

arXiv cs.LG · cs.AINov 6, 2026 #

Towards interpreting any residual stream direction by scaling activation inversion

Explanation and summary in progress

Celeste De Schamphelaere, Juan J. Vazquez, Ari Spiesberger et al.

arXiv cs.LG · math.OCNov 6, 2026 #

Adversarial Training with Large Step Sizes: Implicit Bias, Optimization, and Sharpness

Explanation and summary in progress

Yi Feng, Andrea Paudice

arXiv cs.LG · cs.CLNov 6, 2026 #

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

Explanation and summary in progress

Zeyu Leo Liu, Yang Li, Bo Pang et al.

arXiv cs.AINov 6, 2026 #

ReproBridge: Building Reproducibility into ML Research Artifacts

Explanation and summary in progress

Yubo Wang, Rui Meng, Jaehyun Nam et al.

arXiv cs.RO · cs.CVNov 6, 2026 #

VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding

Explanation and summary in progress

Yu-Cheng Chou, Shihao Wang, Jin Huang et al.

arXiv cs.LGNov 6, 2026 #

A Hidden Markov Preference Model for Online Prediction of Adversary Actions

Explanation and summary in progress

Angel Daruna, Michael Cogswell, Tixiao Shan et al.

arXiv cs.CV · eess.IVNov 6, 2026 #

Edge-Assisted Crowdsensing for Explainable Cyclist Safety Perception

Explanation and summary in progress

Hongsen Cao, Chia-Yen Chiang, Mona Jaber et al.

arXiv cs.CL · cs.AI · cs.LGNov 6, 2026 #

Label-Wording Augmentation in a Typed-Decision Encoder: Gains on Unfamiliar Words, Not on Abbreviations or Codes

Explanation and summary in progress

Vladimir Beskorovainyi

arXiv cs.CL · cs.AI · cs.LGNov 6, 2026 #

Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety

Explanation and summary in progress

Fazl Barez, Tung-Yu Wu, Hunar Batra et al.

arXiv cs.CVNov 6, 2026 #

SM4RT: Cascaded Feed-forward Model for 4D Reconstruction

Explanation and summary in progress

Pang-Chi Lo, Jhao-Syun Lai, Tsung-Wei Ke

arXiv cs.CL · cs.AINov 6, 2026 #

MedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue

Explanation and summary in progress

Donghua Zhang, Zizheng Wang, Ze Dong et al.

arXiv cs.AINov 6, 2026 #

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

Explanation and summary in progress

Julian Kunkel, Ali Doosthosseini

arXiv cs.RO · cs.AINov 6, 2026 #

Failure Prediction and Classification in Vision-Language-Action Models Via Calibrated Latent Probing

Explanation and summary in progress

Michal P. Podolinsky, Yunhao Yang, Daniel Little et al.

arXiv cs.LG · cs.NA · math.DGNov 6, 2026 #

Data-driven discovery of intrinsic Lie point symmetries of differential equation systems

Explanation and summary in progress

Ilker Gurcan, Kadir Ustun, Ramazan Gokberk Cinbis

arXiv cs.LGNov 6, 2026 #

On the limitations of molecular representations

Explanation and summary in progress

Acer Blake, Fergus Imrie, Charlotte M. Deane

arXiv cs.AINov 6, 2026 #

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

Explanation and summary in progress

E. Kelly Buchanan, Crystal Zhou, Scott W. Linderman et al.

arXiv cs.LG · stat.MLNov 6, 2026 #

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

Explanation and summary in progress

Chenruo Liu, Zihan Wang, Yijun Dong et al.

arXiv cs.RO · cs.CVNov 6, 2026 #

T3R: Training-Free Two-Stage Token Refinement Towards Efficient and Robust VLA Models

Explanation and summary in progress

Mohammed Hassan, Zhenyang Chen, Zheng Wang et al.

arXiv cs.AI · stat.APNov 6, 2026 #

The Gold Rush in AI4Math, II: What are signatures of AI-assisted Proofs?

Explanation and summary in progress

Yuanchuan Guo, Jiashun Jin, Zheng Tracy Ke et al.

arXiv cs.LG · stat.MLNov 6, 2026 #

Conformal Prediction for Time-Dependent PDEs

Explanation and summary in progress

Joshua Stiller, Annika Schneider, Eyke H\"ullermeier

arXiv cs.RO · cs.CV · cs.LGNov 6, 2026 #

Social Humanoid: Socially Responsive Human-Humanoid Interaction

Explanation and summary in progress

Vongani H. Maluleke, James Ni, Kie Horiuchi et al.

arXiv cs.AI · cs.CL · cs.LGNov 6, 2026 #

StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning

Explanation and summary in progress

Yang Ouyang, Jung-Eun Kim

arXiv cs.LGNov 6, 2026 #

Synthesis of Ovarian Cancer Multi-Omics Datasets: A Biology-Informed Evaluation Framework

Explanation and summary in progress

D\'eborah Boyenval, Alina Malyutina, Jaana Oikkonen et al.

arXiv cs.CVNov 6, 2026 #

Adaptive Low-Light Enhancement for Road Anomaly Detection: A Multi-Architecture Benchmark and Edge Deployment Study

Explanation and summary in progress

Obed Honour Eje, Oluwatosin Kolade, Glory Bagai et al.

arXiv cs.AINov 6, 2026 #

Learning a patient world model for health system simulation in intensive care

Explanation and summary in progress

Yingtai Li, Ruoyan Wang, Yu Li et al.

arXiv cs.RO · cs.MANov 6, 2026 #

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

Explanation and summary in progress

Shanghao Shi, Jian Xiao, Ching-Hsiang Chan et al.

arXiv cs.LG · cs.AINov 6, 2026 #

Hybrid Machine Learning for Imbalanced Landing-Phase Safety Event Prediction from Flight Data

Explanation and summary in progress

Taha Asghar, Bilal Mufti, Syed Qasim Zaheer et al.

arXiv cs.LGNov 6, 2026 #

Module-Aware Optimization for Graph Neural Networks

Explanation and summary in progress

Guy Hadad, Haggai Roitman, Moshe Eliasof et al.

arXiv cs.LGNov 6, 2026 #

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

Explanation and summary in progress

Tushaar Gangavarapu, Gil Tabak, Clemens JS Schaefer

arXiv cs.RO · cs.AI · cs.CVNov 6, 2026 #

MOMASPLAT: Dynamic Novel-View Demonstration Augmentation for Mobile Manipulation

Explanation and summary in progress

Sateesh Kumar, Arnav Balaji, Arpit Bahety et al.

arXiv cs.AINov 6, 2026 #

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

Explanation and summary in progress

Pengkai Wang, Wei-Wei Zhang, Yan Li et al.

arXiv cs.RO · cs.AI · cs.CVNov 6, 2026 #

VisionSIM: Beyond Idealized Sensors - A Multi-Modal Simulator for Robot Perception

Explanation and summary in progress

Sacha Jungerman, Kaustubh Sadekar, Avery Gump et al.

arXiv cs.RO · cs.LGNov 6, 2026 #

SHORE: Stability-Hybrid On-Policy Reinforcement Learning for Online Bin Packing

Explanation and summary in progress

Chang Shi, Ann Majewicz Fey

arXiv cs.LG · cs.DCNov 6, 2026 #

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

Explanation and summary in progress

Jake Hyun, Ziyu Zhao, Jae-sun Seo et al.

arXiv cs.CLNov 6, 2026 #

SpecCTMC: Exact Speculative Simulation of Diffusion Language Model Continuous-Time Markov Chains

Explanation and summary in progress

Siva Rajesh Kasa, Yasong Dai, Sumit Negi et al.

arXiv cs.RO · cs.MANov 6, 2026 #

Radio-to-Pose Information for Gauge-Drift Correction in Cooperative Localization

Explanation and summary in progress

Aditya Iyer, Andy Ye, Akshay Narayan et al.

arXiv cs.CV · eess.IVNov 6, 2026 #

OraRefer: Segmentation-Guided Multi-Photograph Fusion for Oral Cancer Screening with Guaranteed Patient-Level Sensitivity

Explanation and summary in progress

Rupam Mukherjee, Mehakdeep Singh, Shirin Dasgupta et al.

arXiv math.OC · cs.CVNov 6, 2026 #

A Theoretical Analysis of a Bilevel Optimization Formulation for Combined Local-Global Optical Flow Models

Explanation and summary in progress

El Mostafa Kalmoun

arXiv stat.ML · cs.LGNov 6, 2026 #

Unifying Central Flow, Rod Flow, and the Edge Coupling

Explanation and summary in progress

Eric Regis, Sinho Chewi

arXiv cs.CV · cs.LG · cs.RONov 6, 2026 #

USB Gym: A Gymnasium Testbed for Closed-Loop Ultrasound View Matching

Explanation and summary in progress

Thanapong Intharah, Zhichao Gao, Yiliang Liu et al.

arXiv cs.CV · cs.GR · cs.LGNov 6, 2026 #

4D Point Splatting for mmWave Radar Micro-Doppler Differentiable Rendering

Explanation and summary in progress

Adnan Armouti, Guanyue Qian, Rajalakshmi Nandakumar

arXiv cs.AINov 6, 2026 #

Enhancing Local and Global Structure in Compressed AI Agent Memory

Explanation and summary in progress

Henry Han

arXiv cs.LGNov 6, 2026 #

Discovering Learning Rules that Shape Others

Explanation and summary in progress

Hong Jun Lee, Ziyan Wang, Jun Wang et al.

arXiv cs.CLNov 6, 2026 #

Cultural Adaptation within Repeated Social Interactions

Explanation and summary in progress

Chen Cecilia Liu, Roi Reichart, Anna Korhonen

arXiv cs.CVNov 6, 2026 #

InstantHand: Feed-Forward 3D Gaussian Splatting for Animatable Hand Avatar Reconstruction from a Single Image

Explanation and summary in progress

Chanho Kim, Muhammad Salman Ali, Kyeonghwan Gwak et al.

arXiv cs.CLNov 6, 2026 #

Polarity Classification with Multitask Learning Syntax Augmentation

Explanation and summary in progress

Muhammad Imran, Carlos G\'omez-Rodr\'iguez

arXiv cs.AI · cs.RONov 6, 2026 #

Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement

Explanation and summary in progress

Wenbo Huang, Jianxin Bi, Shunyu Yang et al.

arXiv cs.AI · cs.CL · cs.LGNov 6, 2026 #

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

Explanation and summary in progress

Ali Sarabadani, Kheirolah Rahsepar Fard, Tahereh Jeirani

arXiv cs.LG · physics.bio-ph · q-bio.QMNov 6, 2026 #

Interpretable many-body interaction laws for collective motion from few trajectories

Explanation and summary in progress

Timon S. Gutleb

arXiv cs.MANov 6, 2026 #

Trilemma: How Agents choose between Honesty, Confidentiality, and Task Completion

Explanation and summary in progress

Johannes Taraz, Abhinav Kumar, Sahar Abdelnabi

arXiv cs.CLNov 6, 2026 #

LLM-Assisted Label Noise Correction for EEG-Based Sleep Stage Classification

Explanation and summary in progress

Elmira Salari, Shruti Kshirsagar

arXiv cs.AI · cs.LGNov 6, 2026 #

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

Explanation and summary in progress

Roko Parac, Christos Ziakas, Leo Ardon et al.

arXiv cs.CL · cs.AI · cs.DCNov 6, 2026 #

Measured Coupling for Parallel Decoding in Diffusion Language Models

Explanation and summary in progress

Tal Oved, Lior Wolf

arXiv cs.IR · cs.DCNov 6, 2026 #

GINGER: Spicing Up Graph-Based Vector Search

Explanation and summary in progress

Daniel Salwasser, Lars Gottesb\"uren, Laxman Dhulipala et al.

arXiv cs.AINov 6, 2026 #

First-Token Attraction in Mamba Dynamics

Explanation and summary in progress

Trinh T. Nguyen, Minh-Khoi Nguyen-Nhat, Duy-Tung Pham et al.

arXiv cs.LG · math.OCNov 6, 2026 #

Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence

Explanation and summary in progress

Mohammed Abdullah, George Iosifidis, Salah Eddine Elayoubi et al.

arXiv cs.RO · cs.HC · cs.LGNov 6, 2026 #

Transformer-Based Trajectory Prescription for sEMG-Optimizing Robot-Mediated Rehabilitation

Explanation and summary in progress

Gabriel Parra, Kimia Khoshnami, Daniel S. Brown et al.

arXiv cs.CVNov 6, 2026 #

ManimCode: Learning Visual Self-Correction for Educational Animation

Explanation and summary in progress

Zhengyang Liang, Lizi Liao

arXiv cs.LG · cs.AINov 6, 2026 #

AutoCompress: Automated Hardware-Guided Model Compression

Explanation and summary in progress

Sheldon Liang, Ali Taghibakhshi, Saurav Muralidharan et al.

arXiv cs.CV · cs.GRNov 6, 2026 #

Hierarchical Incremental Beta Splatting for Online Reconstruction

Explanation and summary in progress

Linus Franke

arXiv cs.CVNov 6, 2026 #

Interactive Visual Gym: Evaluating Visual Interaction Models with Simulated Users in Interactive Worlds

Explanation and summary in progress

Chenhao Zheng, Zixian Ma, Kai Li et al.

arXiv cs.AINov 6, 2026 #

A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information Sharing

Explanation and summary in progress

Omer Ebead, Claude Formanek, Joel Z. Leibo

arXiv cs.CLNov 6, 2026 #

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

Explanation and summary in progress

Zhitao He, Chi Him Zhang, Chengru Han et al.

arXiv cs.AINov 6, 2026 #

LeanContext: Disentangling Mathematical Resources from Local Formal Context in Lean Whole-Proof Generation

Explanation and summary in progress

Hang Zhang, Qihao Ye, Litong Liu et al.

arXiv cs.RO · cs.AI · cs.CVNov 6, 2026 #

Aligning Policy Encoders with a Shape Teacher

Explanation and summary in progress

Madelon Bernardy, Mohammad Mahdi Derakhshani, David M Knigge et al.

arXiv cs.LG · cs.AINov 6, 2026 #

Accelerating Safe Reinforcement Learning with Massive Parallelism

Explanation and summary in progress

Joonyoung Lim, Younghwan Yoo

arXiv cs.CV · cs.AI · cs.LGNov 6, 2026 #

DART: Domain-Agnostic Residual Transfer for Generalist Anomaly Detection

Explanation and summary in progress

Muhammad Aqeel, Maham Nazir, Marco Cristani et al.

arXiv cs.SE · cs.AINov 6, 2026 #

Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations

Explanation and summary in progress

Xiaobo Chen, Genliang Zhu, Ziyuan Wang et al.

arXiv cs.CVNov 6, 2026 #

SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes

Explanation and summary in progress

Hao Yu, Zhenwei Wang, Yongzhen Hu et al.

arXiv cs.LG · cs.AINov 6, 2026 #

Scaling Neural Motor Decoding via Decoupled Behavioral Pretraining

Explanation and summary in progress

Divyansha Lachi, Vinam Arora, Shivashriganesh P. Mahato et al.

arXiv cs.AI · cs.CL · cs.CVNov 6, 2026 #

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

Explanation and summary in progress

Mathis Immertreu, Fitim Abdullahu, Thomas Kinfe et al.

arXiv cs.LGNov 6, 2026 #

Nowcasting of Tropical Cyclone Wind Fields and Intensity from Geostationary Imagery

Explanation and summary in progress

Simon Donike, Pritthijit Nath, Cristina Radin et al.

arXiv stat.ML · cs.LGNov 6, 2026 #

Series-wise Cross-validation for Global Time Series Forecasting

Explanation and summary in progress

Vitor Cerqueira, Mariana Oliveira, Luis Roque

arXiv cs.LG · q-bio.BMNov 6, 2026 #

Geometric Relevance Is Not Sufficient: Evaluating Focused Post-Training Supervision in Diffusion Docking

Explanation and summary in progress

Michael Brown, Maryam Rahimimovassagh, Mehdi Yazdani-Jahromi et al.

arXiv cs.AI · cs.SY · eess.SYNov 6, 2026 #

Value-oriented policy distillation for interpretable wind farm power control

Explanation and summary in progress

Max Bruninx, Timothy Verstraeten, Jan Decuyper et al.

arXiv cs.LG · cs.CVNov 6, 2026 #

FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning

Explanation and summary in progress

Haitao Lin, Minsi Ren, Yang Li et al.

arXiv cs.CLNov 6, 2026 #

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

Explanation and summary in progress

Xiaojun Wu, Cehao Yang, Xuhui Jiang et al.

arXiv cs.LG · cs.CVNov 6, 2026 #

Beyond Quadratic Attention: Separable Gaussian Operators for ODE Vision Transformers

Explanation and summary in progress

Carlos Boned Riera, David Romero Sanchez, Oriol Ramos Terrades

arXiv cs.AINov 6, 2026 #

Signals, Evidence, and Context: User Scrutiny in Real-World LLM Conversations

Explanation and summary in progress

Ahana Biswas, Yu-Ru Lin

arXiv cs.CLNov 6, 2026 #

From Twisted Facts to Rogue Agents: Can LLMs Reliably Detect Multi-Dimensional Hallucinations?

Explanation and summary in progress

Hanyu Qiu, Ze Liu, Zhe Zhao et al.

arXiv cs.CY · cs.CL · cs.HCNov 6, 2026 #

"Blind Compliance": Coercive Control in AI Jailbreaking

Explanation and summary in progress

Acacia L. Ackles, Elliott Whitson

arXiv cs.CLNov 6, 2026 #

Agent-R²: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis

Explanation and summary in progress

Teng Pan, Zixuan Wang, Yuchen Yan et al.

arXiv cs.CV · cs.CLNov 6, 2026 #

ProQuant: Progressive Quantization-aware Training for Edge MLLMs

Explanation and summary in progress

Yufei Xue, Yushi Huang, Jiawei Shao et al.

arXiv cs.LG · q-bio.NCNov 6, 2026 #

Do sEMG Foundation Models Improve Cross-Subject Generalisation?

Explanation and summary in progress

William Raftery, Dario Farina

arXiv cs.AI · cs.CLNov 6, 2026 #

SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving

Explanation and summary in progress

Sai Vallurupalli, Francis Ferraro

arXiv cs.CVNov 6, 2026 #

Multimodal Hierarchical Mixture-of-Experts for 3D Medical Vision-Language Modeling

Explanation and summary in progress

Gizem Mert, Szymon P{\l}otka, Pedro R. A. S. Bassi et al.

arXiv cs.LG · stat.MLNov 6, 2026 #

BUMP: Brief Unexpected Mid-Interpolation Peak

Explanation and summary in progress

Melinda Fl\'ora Kiss, M\'arton Muntag, Adri\'an Csisz\'arik et al.

arXiv cs.CL · cs.AINov 6, 2026 #

Knowing When to Teach: Learning from Teachable Prefixes in Multilingual Reasoning Distillation

Explanation and summary in progress

Jaewon Cho, Minseo Yoon, Jinyoung Park et al.

arXiv cs.AINov 6, 2026 #

BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone

Explanation and summary in progress

Doojin Baek, Junyeob Baek, Mingyu Jo et al.

arXiv cs.AINov 6, 2026 #

PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers?

Explanation and summary in progress

Yue Zhang, Jilei Sun, Liqiang Jing et al.

arXiv cs.GT · cs.DS · cs.LGNov 6, 2026 #

Regret Bounds for Profit Maximization in Bilateral Trade: Learning the Best Posted-Price Mechanism

Explanation and summary in progress

Johannes Br\"ustle, Simone Di Gregorio, Federico Fusco et al.

arXiv cs.SE · cs.CLNov 6, 2026 #

RouteAlign: Aligning Task Requirements with Model Profiles for LLM Service Selection

Explanation and summary in progress

Jihao Zhao, Ding Chen, Yanfang Chen et al.