Every paper with a summary

Every arXiv paper Paperlayer has summarized so far. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

24,481 to 24,540 of 119,758

ContactMimic: Humanoid Object Interaction via Contact Control
Xinyao Li, Xialin He, Runpei Dong +1
cs.ROarXiv:2607.08742v12026
Modular Pretraining Enables Access Control
Ethan Roland, Murat Cubuktepe, Erick Martinez +8
cs.LGarXiv:2607.08077v12026
Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions
Haochen Luo, Yi Huang, Sichun Luo +5
cs.AIarXiv:2607.03935v12026
Hyperbolic dynamic friction models for viscoelastic sliding and rolling contact
Luigi Romano
physics.app-pharXiv:2606.09128v112026
MPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical Dynamics
Žiga Kovačič, Kevin Ellis
cs.GRcs.CVcs.LGarXiv:2606.01538v22026
PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents
Zayx Shawn
cs.AIcs.MAarXiv:2606.08106v12026
FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents
Quang Hieu Pham, Yang He, Ping Nie +5
cs.CLarXiv:2605.02815v22026
SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects
Puyi Wang, Yuhao Wang, Linjie Li +4
cs.AIarXiv:2605.19587v12026
Haptic Rendering of Fractional-Order Viscoelasticity: Passivity and Rendering Fidelity
Gorkem Gemalmaz, Harun Tolasa, Volkan Patoglu
cs.ROcs.AIcs.SYarXiv:2605.16389v12026
ClickRemoval: An Interactive Open-Source Tool for Object Removal in Diffusion Models
Ledun Zhang, Yatu Ji, Xufei Zhuang +1
cs.CVarXiv:2605.14461v12026
Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
Xiaozhe Zhang, Chaozhuo Li, Hui Liu +4
cs.CRcs.CLarXiv:2605.13411v12026
JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning
Jing Yu Lim, Rushi Shah, Zarif Ikram +4
cs.LGarXiv:2605.13013v12026
Early Data Exposure Improves Robustness to Subsequent Fine-Tuning
Lawrence Feng, Gaurav R. Ghosal, Jacob Mitchell Springer +2
cs.LGarXiv:2605.12705v22026
A Cellular Doctrine of Morality: Intrinsic Active Precision and the Mind-Reality Overload Dilemma
Ahsan Adeel
cs.AIarXiv:2605.01376v12026
SkillCom: Decomposing LLM-based Semantic Communication into Task and Channel Aware Skills
Jingwen Fu, Ming Xiao, Mikael Skoglund
eess.SYcs.SYarXiv:2605.02333v12026
PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement
Tianyidan Xie, Peiyu Wang, Hu Jiaxin +9
cs.ROcs.AIarXiv:2604.23580v22026
Improving MPI Error Detection and Repair with Large Language Models and Bug References
Scott Piersall, Yang Gao, Shenyang Liu +1
cs.SEcs.AIarXiv:2604.02398v12026
Agentic Forecasting with Structured Linguistic Beliefs
Kevin Murphy
cs.AIarXiv:2604.18576v52026
Where is the Mind? Persona Vectors and LLM Individuation
Pierre Beckmann, Patrick Butlin
cs.CLcs.AIarXiv:2604.17031v32026
Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents
Bhaskar Gurram
cs.AIcs.CLcs.MAarXiv:2604.16706v22026
Audio-Cogito: Towards Deep Audio Reasoning in Large Audio Language Models
Longhao Li, Hongjie Chen, Zehan Li +5
eess.ASarXiv:2604.12527v32026
LVSum: A Benchmark for Timestamp-Aware Long Video Summarization
Alkesh Patel, Melis Ozyildirim, Ying-Chang Cheng +1
cs.CVcs.AIcs.LGarXiv:2604.10024v22026
VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation
Yan Zheng, Florian Bordes
cs.LGarXiv:2604.02580v12026
HumDex: Humanoid Dexterous Manipulation Made Easy
Liang Heng, Yihe Tang, Jiajun Xu +3
cs.ROarXiv:2603.12260v22026
Adaptive Stopping for Multi-Turn LLM Reasoning
Xiaofan Zhou, Huy Nguyen, Bo Yu +2
cs.CLcs.AIarXiv:2604.01413v32026
6GAgentGym: Tool Use, Data Synthesis, and Agentic Learning for Network Management
Jiao Chen, Jianhua Tang, Xiaotong Yang +1
cs.NIcs.AIarXiv:2603.29656v12026
EvoFlows: Evolutionary Edit-Based Flow-Matching for Protein Engineering
Nicolas Deutschmann, Constance Ferragu, Jonathan D. Ziegler +2
cs.LGarXiv:2603.11703v22026
A Duality-Based Optimization Formulation of Safe Control Design with State Uncertainties
Xiao Tan, Rahal Nanayakkara, Paulo Tabuada +1
eess.SYcs.SYarXiv:2603.26999v22026
Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward Models
Weijie Qiu, Dai Guan, Junxin Wang +6
cs.CVarXiv:2603.16600v22026
The Finetuner's Fallacy: When to Pretrain with Your Finetuning Data
Christina Baek, Ricardo Pio Monti, David Schwab +31
cs.LGarXiv:2603.16177v22026
Modeling, Optimization and Electromagnetic Validation of Stacked Intelligent Metasurfaces by Using a Multiport Network Model
Giuseppe Pettanice, Andrea Abrardo, Alberto Toccafondi +1
eess.SParXiv:2603.14266v22026
Diffusion Reinforcement Learning via Centered Reward Distillation
Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière +1
cs.CVcs.AIcs.LGarXiv:2603.14128v12026
FPGA-Based Low-Power Speech Recognition with Recurrent Neural Networks
Minjae Lee, Kyuyeon Hwang, Jinhwan Park +3
cs.CLcs.LGcs.SDarXiv:1610.00552v12016
Quantifying the Accuracy and Cost Impact of Design Decisions in Budget-Constrained Agentic LLM Search
Kyle McCleary, James Ghawaly
cs.AIarXiv:2603.08877v12026
Vision Language Models Cannot Reason About Physical Transformation
Dezhi Luo, Yijiang Li, Maijunxian Wang +7
cs.AIarXiv:2603.07109v22026
Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution
Guoxin Shi, Haoyu Wang, Zaihui Yang +2
cs.CRcs.AIarXiv:2603.01784v12026
S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research
NexusAgent Team
cs.AIarXiv:2602.01550v22026
Prompt Interference in LLM Post-Training: Why Pass@k Optimization Can Degrade Pass@1
Anas Barakat, Souradip Chakraborty, Khushbu Pahwa +1
cs.LGcs.AIarXiv:2602.21189v32026
RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning
Yukun Chen, Jiaming Li, Longze Chen +10
cs.CLarXiv:2602.21628v22026
Improving Sampling for Masked Diffusion Models via Information Gain
Kaisen Yang, Jayden Teoh, Kaicheng Yang +2
cs.CLarXiv:2602.18176v32026
APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL
Bowen Cao, Weibin Liao, Yushi Sun +3
cs.DBcs.AIarXiv:2602.16720v22026
Combined Constrained Sampling and Reinforcement Learning for Robotic Manipulation
Marc Toussaint, Cornelius V. Braun, Armand Jordana +5
cs.ROarXiv:2602.08557v22026
TeleStyle: Content-Preserving Style Transfer in Images and Videos
Shiwen Zhang, Xiaoyan Yang, Bojia Zi +3
cs.CVarXiv:2601.20175v12026
On the stability, complexity, and distribution of similarity classes of the longest edge bisection process for triangles
Daniel Kalmanovich, Yaar Solomon
cs.CGmath.COarXiv:2601.13663v32026
Linear viscoelastic rheological FrBD models
Luigi Romano, Ole Morten Aamo, Jan Åslund +1
eess.SYcs.SYarXiv:2601.13799v32026
Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Research
Derguene Mbaye, Tatiana D. P. Mbengue, Madoune R. Seye +7
cs.CLarXiv:2601.09716v22025
ArchAgent: Scalable Legacy Software Architecture Recovery with LLMs
Rusheng Pan, Bingcheng Mao, Tianyi Ma +1
cs.SEcs.AIarXiv:2601.13007v12026
Situation-Aware Interactive MPC Switching for Autonomous Driving
Shuhao Qi, Qiling Aori, Luyao Zhang +2
cs.ROcs.SYeess.SYarXiv:2512.06182v22025
Multimodal Routing: Improving Local and Global Interpretability of Multimodal Language Analysis
Yao-Hung Hubert Tsai, Martin Q. Ma, Muqiao Yang +2
cs.CLarXiv:2004.14198v22020
Beyond VQA: Generating Multi-word Answer and Rationale to Visual Questions
Radhika Dua, Sai Srinivas Kancheti, Vineeth N Balasubramanian
cs.CVcs.AIarXiv:2010.12852v22020
Towards Transparent AI Systems: Interpreting Visual Question Answering Models
Yash Goyal, Akrit Mohapatra, Devi Parikh +1
cs.CVcs.AIcs.CLarXiv:1608.08974v22016
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models
Roland S. Zimmermann, Thomas Klein, Wieland Brendel
cs.CVarXiv:2307.05471v22023
Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies
Itai Gat, Idan Schwartz, Alexander Schwing +1
cs.CVcs.LGarXiv:2010.10802v12020
Linear Connectivity Reveals Generalization Strategies
Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho +2
cs.LGcs.CLarXiv:2205.12411v52022
Enforcing Temporal Constraints for LLM Agents
Adharsh Kamath, Sishen Zhang, Calvin Xu +3
cs.PLcs.AIcs.FLarXiv:2512.23738v12025
EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal
Sanghyun Jo, Donghwan Lee, Eunji Jung +2
cs.CVarXiv:2512.21545v22025
FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration
Dongwon Jung, Peng Shi, Muhao Chen +1
cs.AIcs.CLarXiv:2512.11213v22025
The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss
Bozhou Li, Xinda Xue, Sihan Yang +5
cs.CVarXiv:2512.08374v12025
When do spectral gradient updates help in deep learning?
Damek Davis, Dmitriy Drusvyatskiy
cs.LGmath.OCstat.MLarXiv:2512.04299v22025
RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
Xuelu Feng, Yunsheng Li, Ziyu Wan +4
cs.CVarXiv:2511.20651v42025

Every paper with a summary

ContactMimic: Humanoid Object Interaction via Contact Control

Modular Pretraining Enables Access Control

Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions

Hyperbolic dynamic friction models for viscoelastic sliding and rolling contact

MPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical Dynamics

PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents

FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents

SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects

Haptic Rendering of Fractional-Order Viscoelasticity: Passivity and Rendering Fidelity

ClickRemoval: An Interactive Open-Source Tool for Object Removal in Diffusion Models

Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution

JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning

Early Data Exposure Improves Robustness to Subsequent Fine-Tuning

A Cellular Doctrine of Morality: Intrinsic Active Precision and the Mind-Reality Overload Dilemma

SkillCom: Decomposing LLM-based Semantic Communication into Task and Channel Aware Skills

PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement

Improving MPI Error Detection and Repair with Large Language Models and Bug References

Agentic Forecasting with Structured Linguistic Beliefs

Where is the Mind? Persona Vectors and LLM Individuation

Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents

Audio-Cogito: Towards Deep Audio Reasoning in Large Audio Language Models

LVSum: A Benchmark for Timestamp-Aware Long Video Summarization

VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation

HumDex: Humanoid Dexterous Manipulation Made Easy

Adaptive Stopping for Multi-Turn LLM Reasoning

6GAgentGym: Tool Use, Data Synthesis, and Agentic Learning for Network Management

EvoFlows: Evolutionary Edit-Based Flow-Matching for Protein Engineering

A Duality-Based Optimization Formulation of Safe Control Design with State Uncertainties

Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward Models

The Finetuner's Fallacy: When to Pretrain with Your Finetuning Data

Modeling, Optimization and Electromagnetic Validation of Stacked Intelligent Metasurfaces by Using a Multiport Network Model

Diffusion Reinforcement Learning via Centered Reward Distillation

FPGA-Based Low-Power Speech Recognition with Recurrent Neural Networks

Quantifying the Accuracy and Cost Impact of Design Decisions in Budget-Constrained Agentic LLM Search

Vision Language Models Cannot Reason About Physical Transformation

Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution

S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research

Prompt Interference in LLM Post-Training: Why Pass@k Optimization Can Degrade Pass@1

RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning

Improving Sampling for Masked Diffusion Models via Information Gain

APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL

Combined Constrained Sampling and Reinforcement Learning for Robotic Manipulation

TeleStyle: Content-Preserving Style Transfer in Images and Videos

On the stability, complexity, and distribution of similarity classes of the longest edge bisection process for triangles

Linear viscoelastic rheological FrBD models

Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Research

ArchAgent: Scalable Legacy Software Architecture Recovery with LLMs

Situation-Aware Interactive MPC Switching for Autonomous Driving

Multimodal Routing: Improving Local and Global Interpretability of Multimodal Language Analysis

Beyond VQA: Generating Multi-word Answer and Rationale to Visual Questions

Towards Transparent AI Systems: Interpreting Visual Question Answering Models

Scale Alone Does not Improve Mechanistic Interpretability in Vision Models

Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies

Linear Connectivity Reveals Generalization Strategies

Enforcing Temporal Constraints for LLM Agents

EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal

FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration

The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss

When do spectral gradient updates help in deep learning?

RubricRL: Simple Generalizable Rewards for Text-to-Image Generation