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)

54,781 to 54,840 of 61,245

Efficient RL Training for LLMs with Experience Replay
Charles Arnal, Vivien Cabannes, Taco Cohen +2
cs.LGarXiv:2604.08706v12026
ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
Boyuan Wang, Xiaofeng Wang, Yongkang Li +9
cs.CVarXiv:2604.07882v12026
Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
Sai Srinivas Kancheti, Aditya Kanade, Rohit Sinha +2
cs.CVcs.AIarXiv:2604.08476v12026
3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
Makanjuola Ogunleye, Eman Abdelrahman, Ismini Lourentzou
cs.CVcs.AIcs.LGarXiv:2604.08645v12026
EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers
Yi-Lun Liao, Alexander J. Hoffman, Sabrina C. Shen +3
cs.LGcs.AIphysics.comp-pharXiv:2604.09130v12026
Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types
Hadas Orgad, Boyi Wei, Kaden Zheng +4
cs.CLcs.AIcs.LGarXiv:2604.09544v22026
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
Lifeng Chen, Tianqi You, Hao Liu +8
cs.LGcs.AIeess.IVarXiv:2604.09450v22026
TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction
Ao Li, Yonggen Ling, Yiyang Lin +3
cs.CVarXiv:2604.08921v12026
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
Rui Xu, Dafei Qin, Kaichun Qiao +8
cs.CVcs.CGcs.GRarXiv:2604.09132v22026
Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling
Ximing Xing, Ziteng Xue, Zhenxi Li +8
cs.LGarXiv:2604.05072v22026
Many-Tier Instruction Hierarchy in LLM Agents
Jingyu Zhang, Tianjian Li, William Jurayj +3
cs.CLcs.AIarXiv:2604.09443v32026
Learning Long-term Motion Embeddings for Efficient Kinematics Generation
Nick Stracke, Kolja Bauer, Stefan Andreas Baumann +3
cs.CVarXiv:2604.11737v12026
Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
Ivan Sedykh, Nikita Sorokin, Valentin Malykh
cs.LGcs.CLarXiv:2604.02340v22026
Do AI Coding Agents Log Like Humans? An Empirical Study
Youssef Esseddiq Ouatiti, Mohammed Sayagh, Hao Li +1
cs.SEarXiv:2604.09409v12026
A Temporally Augmented Graph Attention Network for Affordance Classification
Ami Chopra, Supriya Bordoloi, Shyamanta M. Hazarika
cs.LGcs.AIarXiv:2604.10149v12026
Beyond Perception Errors: Semantic Fixation in Large Vision-Language Models
Md Tanvirul Alam
cs.CVcs.LGarXiv:2604.12119v12026
TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
Yinyi Luo, Wenwen Wang, Hayes Bai +6
cs.AIarXiv:2604.10784v22026
ADD for Multi-Bit Image Watermarking
An Luo, Jie Ding
stat.MLcs.AIcs.LGarXiv:2604.11491v12026
Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series
Krzysztof Ociepa, Łukasz Flis, Remigiusz Kinas +2
cs.CLcs.AIarXiv:2604.10799v12026
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
Gregory N. Frank
cs.CLcs.AIcs.LGarXiv:2604.04385v52026
Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
Sreyan Ghosh, Arushi Goel, Kaousheik Jayakumar +15
cs.SDcs.AIcs.CLarXiv:2604.10905v12026
Universal statistical signatures of evolution in artificial intelligence architectures
Theodor Spiro
q-bio.PEcs.AIcs.CYarXiv:2604.10571v12026
Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions
Seongyu Kim, Seungwoo Lee, Hyeonggon Ryu +2
cs.CVarXiv:2604.11579v12026
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
Hanqi Xiao, Vaidehi Patil, Zaid Khan +3
cs.CLcs.AIcs.LGarXiv:2604.11666v22026
Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation
Sandro Andric
cs.LGcs.AIcs.CYarXiv:2604.11840v32026
Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach
Haolin Li, Shuyang Jiang, Ruipeng Zhang +3
cs.LGcs.CLarXiv:2604.11547v12026
Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing
Zeyue Tian, Binxin Yang, Zhaoyang Liu +8
cs.SDcs.AIcs.CVarXiv:2604.10708v22026
Continuous Adversarial Flow Models
Shanchuan Lin, Ceyuan Yang, Zhijie Lin +2
cs.LGcs.CVarXiv:2604.11521v12026
Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
Mihir Prabhudesai, Aryan Satpathy, Yangmin Li +6
cs.LGcs.AIcs.CVarXiv:2604.11805v12026
SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering
Ningyan Zhu, Huacan Wang, Jie Zhou +8
cs.AIarXiv:2604.11548v12026
LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment
Dujun Nie, Fengjiao Chen, Qi Lv +4
cs.CVcs.ROarXiv:2604.11689v12026
Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
Samuel Cahyawijaya, Peerat Limkonchotiwat, Tack Hwa Wong +45
cs.AIcs.CLcs.CVarXiv:2604.11490v22026
HDR Video Generation via Latent Alignment with Logarithmic Encoding
Naomi Ken Korem, Mohamed Oumoumad, Harel Cain +6
cs.CVarXiv:2604.11788v12026
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
Tianyi Wang, Yixia Li, Long Li +6
cs.AIarXiv:2604.08865v12026
Zero-shot World Models Are Developmentally Efficient Learners
Khai Loong Aw, Klemen Kotar, Wanhee Lee +6
cs.AIcs.CVarXiv:2604.10333v12026
Counting to Four is still a Chore for VLMs
Duy Le Dinh Anh, Patrick Amadeus Irawan, Tuan Van Vo
cs.CVarXiv:2604.10039v12026
Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation
Gordon Chen, Ziqi Huang, Ziwei Liu
cs.CVarXiv:2604.10030v12026
EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model
Kunho Kim, Sumin Seo, Yongjun Cho +1
cs.CVarXiv:2604.10268v12026
SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?
Udari Madhushani Sehwag, Elaine Lau, Haniyeh Ehsani Oskouie +14
cs.AIarXiv:2604.10718v12026
BMdataset: A Musicologically Curated LilyPond Dataset
Matteo Spanio, Ilay Guler, Antonio Rodà
cs.SDcs.CLcs.IRarXiv:2604.10628v22026
DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain
Song Jin, Juntian Zhang, Xun Zhang +6
cs.CVarXiv:2604.10425v12026
IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs
Yuzhen Mao, Qitong Wang, Martin Ester +1
cs.LGcs.AIarXiv:2604.10539v12026
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs
Yu Li, Xiaoran Shang, Qizhi Pei +11
cs.AIarXiv:2604.10480v12026
PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents
Mikhail Menschikov, Dmitry Evseev, Victoria Dochkina +5
cs.CLcs.IRarXiv:2506.17001v62025
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
Xuwei Ding, Skylar Zhai, Linxin Song +6
cs.CRcs.AIarXiv:2604.10577v22026
Rethinking the Diffusion Model from a Langevin Perspective
Candi Zheng, Yuan Lan
cs.LGcs.AIcs.CVarXiv:2604.10465v12026
PokeRL: Reinforcement Learning for Pokemon Red
Dheeraj Mudireddy, Sai Patibandla
cs.LGarXiv:2604.10812v12026
Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
Zhipeng Chen, Tao Qian, Wayne Xin Zhao +1
cs.LGcs.AIcs.CLarXiv:2604.11446v12026
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
Weixian Waylon Li, Jiaxin Zhang, Xianan Jim Yang +2
cs.CLcs.AIarXiv:2604.11544v12026
SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
Shuquan Lian, Juncheng Liu, Yazhe Chen +2
cs.AIcs.CLarXiv:2604.11716v12026
Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
Zhixin Lin, Jungang Li, Dongliang Xu +5
cs.AIcs.CRarXiv:2604.11259v12026
From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models
Chenchen Zhang
cs.CLarXiv:2604.09459v32026
General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks
Junlin Liu, Shengnan An, Shuang Zhou +10
cs.CLcs.AIarXiv:2604.11778v12026
Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
Yoonsang Lee, Howard Yen, Xi Ye +1
cs.CLarXiv:2604.11753v32026
Introspective Diffusion Language Models
Yifan Yu, Yuqing Jian, Junxiong Wang +12
cs.AIarXiv:2604.11035v12026
CocoaBench: Evaluating Unified Digital Agents in the Wild
CocoaBench Team, Shibo Hao, Zhining Zhang +29
cs.CLcs.AIarXiv:2604.11201v22026
Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models
Songlin Yang, Xianghao Kong, Anyi Rao
cs.CVcs.AIarXiv:2604.10949v12026
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation
Donghao Zhou, Guisheng Liu, Hao Yang +9
cs.CVarXiv:2604.11804v22026
CodeTracer: Towards Traceable Agent States
Han Li, Yifan Yao, Letian Zhu +13
cs.SEcs.AIarXiv:2604.11641v32026
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
Yang Liu, Enxi Wang, Yufei Gao +6
cs.LGcs.AIcs.CLarXiv:2604.11297v12026

Every paper with a summary

Efficient RL Training for LLMs with Experience Replay

ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video

Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization

3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding

EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers

Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types

ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion

TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction

Strips as Tokens: Artist Mesh Generation with Native UV Segmentation

Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling

Many-Tier Instruction Hierarchy in LLM Agents

Learning Long-term Motion Embeddings for Efficient Kinematics Generation

Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models

Do AI Coding Agents Log Like Humans? An Empirical Study

A Temporally Augmented Graph Attention Network for Affordance Classification

Beyond Perception Errors: Semantic Fixation in Large Vision-Language Models

TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training

ADD for Multi-Bit Image Watermarking

Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music

Universal statistical signatures of evolution in artificial intelligence architectures

Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions

Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind

Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation

Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach

Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing

Continuous Adversarial Flow Models

Solving Physics Olympiad via Reinforcement Learning on Physics Simulators

SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering

LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment

Anthropogenic Regional Adaptation in Multimodal Vision-Language Model

HDR Video Generation via Latent Alignment with Logarithmic Encoding

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

Zero-shot World Models Are Developmentally Efficient Learners

Counting to Four is still a Chore for VLMs

Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation

EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model

SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?

BMdataset: A Musicologically Curated LilyPond Dataset

DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain

IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs

Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs

PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

Rethinking the Diffusion Model from a Langevin Perspective

PokeRL: Reinforcement Learning for Pokemon Red

Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration

Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory

SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context

Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization

From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models

General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks

Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks

Introspective Diffusion Language Models

CocoaBench: Evaluating Unified Digital Agents in the Wild

Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models

OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation

CodeTracer: Towards Traceable Agent States

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping