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)

54,841 to 54,900 of 61,428

InCoder-32B-Thinking: Industrial Code World Model for Thinking
Jian Yang, Wei Zhang, Jiajun Wu +22
cs.ARcs.AIcs.CLarXiv:2604.03144v12026
Do Audio-Visual Large Language Models Really See and Hear?
Ramaneswaran Selvakumar, Kaousheik Jayakumar, S Sakshi +3
cs.AIcs.SDarXiv:2604.02605v12026
Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models
Sarath Shekkizhar, Romain Cosentino, Adam Earle
cs.AIarXiv:2604.02315v22026
LightThinker++: From Reasoning Compression to Memory Management
Yuqi Zhu, Jintian Zhang, Zhenjie Wan +7
cs.CLcs.AIcs.IRarXiv:2604.03679v12026
POEMetric: The Last Stanza of Humanity
Bingru Li, Han Wang, Hazel Wilkinson
cs.CLarXiv:2604.03695v12026
Training a Student Expert via Semi-Supervised Foundation Model Distillation
Pardis Taghavi, Tian Liu, Renjie Li +2
cs.CVarXiv:2604.03841v12026
Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?
Peter Yongho Kim, Juhyeon Park, Jungwoo Park +4
cs.CVarXiv:2604.03619v12026
Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents
Ádám Kovács
cs.SEcs.AIarXiv:2604.04979v12026
Can LLMs Learn to Reason Robustly under Noisy Supervision?
Shenzhi Yang, Guangcheng Zhu, Bowen Song +7
cs.LGcs.AIarXiv:2604.03993v12026
AURA: Always-On Understanding and Real-Time Assistance via Video Streams
Xudong Lu, Yang Bo, Jinpeng Chen +9
cs.CVarXiv:2604.04184v12026
DARE: Diffusion Large Language Models Alignment and Reinforcement Executor
Jingyi Yang, Yuxian Jiang, Xuhao Hu +3
cs.CLarXiv:2604.04215v12026
A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning
Tianle Chen, Deepti Ghadiyaram
cs.CVcs.SDarXiv:2604.03995v12026
HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systems
Asiri Dalugoda
cs.CRcs.MAarXiv:2604.04522v12026
CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models
Xiangzhao Hao, Zefeng Zhang, Zhenyu Zhang +6
cs.CVarXiv:2604.04780v12026
AvatarPointillist: AutoRegressive 4D Gaussian Avatarization
Hongyu Liu, Xuan Wang, Zijian Wu +7
cs.CVarXiv:2604.04787v22026
Vero: An Open RL Recipe for General Visual Reasoning
Gabriel Sarch, Linrong Cai, Qunzhong Wang +3
cs.CVcs.AIcs.CLarXiv:2604.04917v32026
Paper Espresso: From Paper Overload to Research Insight
Mingzhe Du, Luu Anh Tuan, Dong Huang +1
cs.DLcs.AIarXiv:2604.04562v12026
Less Detail, Better Answers: Degradation-Driven Prompting for VQA
Haoxuan Han, Weijie Wang, Zeyu Zhang +2
cs.CVarXiv:2604.04838v22026
Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
Zijun Wang, Haoqin Tu, Letian Zhang +11
cs.CRcs.AIcs.CLarXiv:2604.04759v12026
FileGram: Grounding Agent Personalization in File-System Behavioral Traces
Shuai Liu, Shulin Tian, Kairui Hu +6
cs.CVcs.AIarXiv:2604.04901v12026
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
DataFlow Team, Bohan Zeng, Daili Hua +39
cs.CVarXiv:2604.04707v22026
REAM: Merging Improves Pruning of Experts in LLMs
Saurav Jha, Maryam Hashemzadeh, Ali Saheb Pasand +3
cs.AIcs.CLcs.LGarXiv:2604.04356v12026
MedGemma 1.5 Technical Report
Andrew Sellergren, Chufan Gao, Fereshteh Mahvar +39
cs.AIarXiv:2604.05081v22026
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Bin Wang, Tianyao He, Linke Ouyang +40
cs.CVcs.CLarXiv:2604.04771v22026
ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
Xiangyi Li, Kyoung Whan Choe, Yimin Liu +12
cs.AIarXiv:2604.05172v22026
MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts
Weiyue Li, Ruizhi Qian, Yi Li +5
cs.CLcs.AIarXiv:2604.06505v12026
GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos
Yiqian Wu, Rawal Khirodkar, Egor Zakharov +6
cs.CVarXiv:2604.07273v22026
Neural Computers
Mingchen Zhuge, Changsheng Zhao, Haozhe Liu +16
cs.LGcs.AIarXiv:2604.06425v22026
How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
Yujian Liu, Jiabao Ji, Li An +3
cs.CLarXiv:2604.04323v12026
Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
Hyunsoo Cha, Wonjung Woo, Byungjun Kim +1
cs.CVarXiv:2604.04934v22026
R3PM-Net: Real-time, Robust, Real-world Point Matching Network
Yasaman Kashefbahrami, Erkut Akdag, Panagiotis Meletis +3
cs.CVcs.LGarXiv:2604.05060v22026
FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios
Xiangru Jian, Hao Xu, Wei Pang +13
cs.CVcs.AIcs.LGarXiv:2604.07413v22026
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
Varun Pratap Bhardwaj
cs.AIcs.CLcs.IRarXiv:2604.04514v12026
CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation
Siddharth Jain, Venkat Narayan Vedam
cs.IRcs.CLcs.LGarXiv:2604.05467v12026
DeonticBench: A Benchmark for Reasoning over Rules
Guangyao Dou, Luis Brena, Akhil Deo +4
cs.CLarXiv:2604.04443v12026
Can Large Language Models Reinvent Foundational Algorithms?
Jian Zhao, Haoren Luo, Yu Wang +3
cs.AIarXiv:2604.05716v12026
MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control
Yuchi Wang, Haiyang Yu, Weikang Bian +4
cs.CVcs.AIcs.CLarXiv:2604.06156v12026
FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification
Ling Yue, Chaoqian Ouyang, Hang Xu +7
cs.AIcs.LGarXiv:2604.04074v42026
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Qihan Ren, Peng Wang, Ruikun Cai +8
cs.AIarXiv:2604.06628v22026
Qualixar OS: A Universal Operating System for AI Agent Orchestration
Varun Pratap Bhardwaj
cs.AIcs.MAcs.SEarXiv:2604.06392v12026
UniSpace: Unified Visual Representation and Scalable Multimodal Modeling
Jinbo Yan, Limeng Qiao, Jie Qin +3
cs.CVcs.AIarXiv:2608.08676v12026
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
Tencent Robotics X, HY Vision Team, : +20
cs.CVarXiv:2604.07430v12026
OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence
Jianhui Liu, Haoze Sun, Wenbo Li +11
cs.CLarXiv:2604.07296v22026
Personalizing Text-to-Image Generation to Individual Taste
Anne-Sofie Maerten, Juliane Verwiebe, Shyamgopal Karthik +3
cs.CVarXiv:2604.07427v12026
MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU
Zhengqing Yuan, Hanchi Sun, Lichao Sun +1
cs.CLcs.DCcs.OSarXiv:2604.05091v12026
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Chaoyou Fu, Haozhi Yuan, Yuhao Dong +16
cs.CVarXiv:2604.05015v12026
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
Tommie Kerssies, Gabriele Berton, Ju He +5
cs.CVarXiv:2604.04913v12026
Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval
Youngjoon Jang, Seongtae Hong, Hyeonseok Moon +1
cs.IRarXiv:2604.04734v22026
STEER: Structured Event Evidence for Video Reasoning via Multi-Objective Reinforcement Learning
Zinuo Li, Yongxin Guo, Jun Liu +7
cs.CLarXiv:2604.04415v32026
SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
Le Chen, Erhu Feng, Yubin Xia +1
cs.SEcs.LGarXiv:2604.03088v32026
Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning
Juekai Lin, Yun Zhu, Honglin Lin +6
cs.CVcs.AIarXiv:2604.06079v12026
RAGEN-2: Reasoning Collapse in Agentic RL
Zihan Wang, Chi Gui, Xing Jin +13
cs.LGarXiv:2604.06268v12026
Target Policy Optimization
Jean Kaddour
cs.LGarXiv:2604.06159v12026
TRACE: Capability-Targeted Agentic Training
Hangoo Kang, Tarun Suresh, Jon Saad-Falcon +1
cs.AIarXiv:2604.05336v22026
The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment
Rishab Balasubramanian, Pin-Jie Lin, Rituraj Sharma +6
cs.LGcs.AIarXiv:2604.06377v32026
Action Images: End-to-End Policy Learning via Multiview Video Generation
Haoyu Zhen, Zixian Gao, Qiao Sun +7
cs.CVcs.ROarXiv:2604.06168v22026
Experience Transfer for Multimodal LLM Agents in Minecraft Game
Chenghao Li, Jun Liu, Songbo Zhang +7
cs.AIarXiv:2604.05533v12026
The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
Yi Xu, Philipp Jettkant, Laura Ruis
cs.LGcs.AIcs.CLarXiv:2604.06427v12026
In-Place Test-Time Training
Guhao Feng, Shengjie Luo, Kai Hua +4
cs.LGcs.AIcs.CLarXiv:2604.06169v12026
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
Qisheng Su, Shiting Huang, Zhen Fang +3
cs.PFcs.SEarXiv:2604.05404v22026

Every paper with a summary

InCoder-32B-Thinking: Industrial Code World Model for Thinking

Do Audio-Visual Large Language Models Really See and Hear?

Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models

LightThinker++: From Reasoning Compression to Memory Management

POEMetric: The Last Stanza of Humanity

Training a Student Expert via Semi-Supervised Foundation Model Distillation

Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?

Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents

Can LLMs Learn to Reason Robustly under Noisy Supervision?

AURA: Always-On Understanding and Real-Time Assistance via Video Streams

DARE: Diffusion Large Language Models Alignment and Reinforcement Executor

A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning

HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systems

CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models

AvatarPointillist: AutoRegressive 4D Gaussian Avatarization

Vero: An Open RL Recipe for General Visual Reasoning

Paper Espresso: From Paper Overload to Research Insight

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

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

FileGram: Grounding Agent Personalization in File-System Behavioral Traces

OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

REAM: Merging Improves Pruning of Experts in LLMs

MedGemma 1.5 Technical Report

MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale

ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces

MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts

GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos

Neural Computers

How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision

R3PM-Net: Real-time, Robust, Real-world Point Matching Network

FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios

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

CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation

DeonticBench: A Benchmark for Reasoning over Rules

Can Large Language Models Reinvent Foundational Algorithms?

MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control

FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Qualixar OS: A Universal Operating System for AI Agent Orchestration

UniSpace: Unified Visual Representation and Scalable Multimodal Modeling

HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence

Personalizing Text-to-Image Generation to Individual Taste

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens

Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval

STEER: Structured Event Evidence for Video Reasoning via Multi-Objective Reinforcement Learning

SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses

Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning

RAGEN-2: Reasoning Collapse in Agentic RL

Target Policy Optimization

TRACE: Capability-Targeted Agentic Training

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment

Action Images: End-to-End Policy Learning via Multiview Video Generation

Experience Transfer for Multimodal LLM Agents in Minecraft Game

The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning

In-Place Test-Time Training

Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning