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)

60,361 to 60,420 of 61,181

Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation
Atin Pothiraj, Jaemin Cho, Yue Zhang +2
cs.CVcs.AIarXiv:2606.25306v12026
Transition-Aware best-of-N sampling for Longitudinal Chest X-ray Reports
Halil Ibrahim Gulluk, Max Van Puyvelde, Wim Van Criekinge +1
cs.CVarXiv:2606.28393v12026
COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami
Tom Zahavy, Shaobo Hou, Thomas Tumiel +16
cs.AIarXiv:2606.26299v12026
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Changdae Oh, Wendi Li, Seongheon Park +3
cs.LGcs.AIarXiv:2606.26080v12026
The Galaxy's Guide to the Tokenizer: A Benchmark for Scientific Foundation Models
Sogol Sanjaripour, Michael J. Smith, Manuel Pérez-Carrasco +3
astro-ph.IMastro-ph.GAarXiv:2606.25610v12026
Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?
Tyler Ga Wei Lum, Kushal Kedia, C. Karen Liu +1
cs.ROcs.AIarXiv:2606.26428v22026
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
Yang Chen, Xiaowei Xu, Shuai Wang +4
cs.CVarXiv:2606.26016v32026
The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar
Ilseyar Alimova, Bogdan Monogov, Artyom Mazur +5
cs.CLarXiv:2606.26015v12026
PhysiFormer: Learning to Simulate Mechanics in World Space
Yiming Chen, Yushi Lan, Andrea Vedaldi
cs.CVarXiv:2606.27364v12026
In-Context World Modeling for Robotic Control
Siyin Wang, Junhao Shi, Senyu Fei +4
cs.ROcs.CVarXiv:2606.26025v32026
Information-Aware KV Cache Compression for Long Reasoning
Jushi Kai, Zhuiri Xiao, Alexandra Birch +1
cs.CLcs.AIarXiv:2606.26875v12026
One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications
Szu-Wei Fu, Rong Chao, Xuesong Yang +4
cs.SDarXiv:2606.25621v22026
Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)
Ilia Larchenko
cs.ROcs.AIcs.LGarXiv:2606.27163v22026
How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring
Zhihao Lin, Mingyi Zhou, Yizhuo Yang +1
cs.SEarXiv:2606.26979v22026
Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents
Minbyul Jeong
cs.CLarXiv:2606.27595v12026
Qwen-Image-2.0-RL Technical Report
Yixian Xu, Kaiyuan Gao, Yuxiang Chen +25
cs.CVcs.LGarXiv:2606.27608v12026
NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning
Tianlin Pan, Lianyu Pang, Cheng Da +4
cs.LGcs.CVarXiv:2606.27771v52026
MultiHashFormer: Hash-based Generative Language Models
Huiyin Xue, Atsuki Yamaguchi, Nikolaos Aletras
cs.CLcs.AIcs.LGarXiv:2606.28057v12026
GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
Xiaocheng Yang, Abdulrahman Alrabah, Dilek Hakkani-Tür +1
cs.MAarXiv:2606.28187v12026
How Good Can Linear Models Be for Time-Series Forecasting?
Lang Huang, Jinglue Xu, Luke Darlow
cs.LGarXiv:2606.27282v22026
Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
Jiayi Xu, Di He, Guolin Ke
cs.CVcs.AIarXiv:2606.27978v12026
Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE
Haoyou Deng, Keyu Yan, Chaojie Mao +4
cs.CVarXiv:2606.26938v12026
A Gravitational Interpretation of Fine-Tuning Reversion
Samuele Poppi, Nils Lukas
cs.LGcs.AIarXiv:2606.28525v12026
Towards Automating Scientific Review with Google's Paper Assistant Tool
Rajesh Jayaram, Drew Tyler, David Woodruff +4
cs.LGcs.AIcs.CLarXiv:2606.28277v12026
ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval
Siqiao Xue, Chunxue Xu
cs.CVarXiv:2606.27708v12026
When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search
Yiling Tao, Shihan Deng, Meiling Tao +3
cs.CLarXiv:2606.27669v22026
ReFreeKV: Towards Threshold-Free KV Cache Compression
Xuanfan Ni, Liyan Xu, Chenyang Lyu +6
cs.CLcs.AIcs.LGarXiv:2502.16886v42025
One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models
Xiaohao Xu, Feng Xue, Xiang Li +5
cs.CVcs.AIarXiv:2606.29600v12026
Geometric Stability of Neural Population Codes: Regional Variation, Behavioral Relevance, and Circuit Dependence
Prashant C. Raju
q-bio.NCcs.NEq-bio.QMarXiv:2606.29655v12026
Learning Transferable Dynamics Priors from Action to World Modeling
Ze Huang, Jiahui Zhang, Hairuo Liu +3
cs.ROarXiv:2606.29501v12026
PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents
Seongjae Kang, Taehyung Yu, Sung Ju Hwang
cs.AIcs.CLarXiv:2606.29225v12026
Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation
Chonghuinan Wang, Zhikai Chen, Chunwei Wang +9
cs.CVarXiv:2606.30054v12026
One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding
Chen Liu, Ling Chen, Hanzhang Zhou +5
cs.CVarXiv:2606.30084v12026
Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark
Matthias Blaschke, Daniel Kienzle, Zsuzsanna Koczor-Benda +3
cs.LGcond-mat.mes-hallcs.AIarXiv:2606.30170v12026
SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing
Jiacheng Zhang, Haoyu He, Sen Zhang +5
cs.AIarXiv:2606.29887v12026
DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model
Daniyel Ayupov, Artur Markov-Tsoy
cs.LGcs.CVarXiv:2606.30292v12026
Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis
Shufan Li, Greg Heinrich, Hanrong Ye +4
cs.CVarXiv:2606.29814v22026
BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language
Haitao Wu, Qirui Zhang, Zhouheng Yao +8
cs.CVcs.LGarXiv:2606.30319v12026
CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion
Pan Wang, Yihao Hu, Xiujin Liu
cs.CVarXiv:2606.30030v12026
One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining
Philip Zmushko, Egor Petrov, Nursultan Abdullaev +2
cs.LGarXiv:2606.30634v12026
LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents
Yogeswar Reddy Thota
cs.OScs.AIcs.CVarXiv:2606.30697v12026
Unlocking the Visual Record of Materials Science: A Large-Scale Multimodal Dataset from Scientific Literature
Subham Ghosh, Shubham Tiwari, Mohammad Ibrahim +1
cs.CVcond-mat.mtrl-scics.AIarXiv:2606.29667v12026
SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation
Zhiyuan Ma, Zhengfeng Shi, Yuning An +6
cs.CVarXiv:2606.30124v12026
Little Brains, Big Feats: Exploring Compact Language Models
Dari Baturova, Elena Bruches, Ivan Chernov +3
cs.CLcs.AIarXiv:2606.30062v12026
JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications
Oxygen AIIC, Chan Long, Chao Liu +52
cs.AIarXiv:2606.28070v22026
Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing
Sen Liang, Cong Wang, Zhentao Yu +8
cs.CVarXiv:2606.30599v22026
DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation
Peyman Hosseini, Ondrej Bohdal, Ahmed Alajrami +6
cs.LGcs.AIarXiv:2606.29961v12026
Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care
Shreyas Rajesh, Kartik Sharma, Tonmoy Monsoor +8
cs.LGarXiv:2606.31036v12026
3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance
Dongyoon Hwang, Byungkun Lee, Dongjin Kim +7
cs.ROcs.AIarXiv:2606.31329v22026
MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs
Yuxuan Fan, Gyusik Seo, Jing Hao +3
cs.CVcs.AIarXiv:2606.30026v12026
RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue
Zhihao Lin, Mingyi Zhou, Zhensu Sun +4
cs.SEarXiv:2607.01213v12026
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
Jisen Li, Bingxuan Li, Nanyi Jiang +10
cs.CLcs.IRarXiv:2607.00597v22026
Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs
Yoonhyung Park, Minji Kim, Sungwon Moon +1
cs.CVcs.MMcs.ROarXiv:2607.00302v12026
When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers
Yushi Sun, Bowen Cao, Wai Lam
cs.DBcs.CLarXiv:2607.00394v12026
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
Mingzhe Du, Luu Anh Tuan, Tianyi Wu +4
cs.AIarXiv:2607.01764v12026
Rank-Then-Act: Reward-Free Control from Frame-Order Progress
Yuriy Maksyuta, George Bredis, Ruslan Rakhimov +1
cs.LGcs.AIarXiv:2607.01897v12026
Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment
Anisha Pattanayak, Hanie Kang, Huang-Cheng Chou +2
eess.ASarXiv:2607.02920v12026
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
Xinyin Ma, Julius Berner, Chao Liu +3
cs.CVarXiv:2607.03509v12026
Spectral Rewiring for Exploration, Purification, and Model Merging
Zhilong Zhang, Hongli Yu, Huan-ang Gao +5
cs.LGcs.AIarXiv:2607.03065v12026
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction
Zhuoqun Li, Boxi Cao, Jiawei Chen +11
cs.CLarXiv:2607.02881v12026

Every paper with a summary

Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation

Transition-Aware best-of-N sampling for Longitudinal Chest X-ray Reports

COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

The Galaxy's Guide to the Tokenizer: A Benchmark for Scientific Foundation Models

Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?

MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation

The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar

PhysiFormer: Learning to Simulate Mechanics in World Space

In-Context World Modeling for Robotic Control

Information-Aware KV Cache Compression for Long Reasoning

One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications

Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)

How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring

Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents

Qwen-Image-2.0-RL Technical Report

NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning

MultiHashFormer: Hash-based Generative Language Models

GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems

How Good Can Linear Models Be for Time-Series Forecasting?

Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation

Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE

A Gravitational Interpretation of Fine-Tuning Reversion

Towards Automating Scientific Review with Google's Paper Assistant Tool

ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval

When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search

ReFreeKV: Towards Threshold-Free KV Cache Compression

One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models

Geometric Stability of Neural Population Codes: Regional Variation, Behavioral Relevance, and Circuit Dependence

Learning Transferable Dynamics Priors from Action to World Modeling

PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents

Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation

One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding

Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark

SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing

DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model

Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis

BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language

CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion

One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining

LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents

Unlocking the Visual Record of Materials Science: A Large-Scale Multimodal Dataset from Scientific Literature

SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation

Little Brains, Big Feats: Exploring Compact Language Models

JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications

Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing

DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation

Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care

3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance

MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs

RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue

Multi-Turn Agentic Scientific Literature Search via Workflow Induction

Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs

When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers

Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction

Rank-Then-Act: Reward-Free Control from Frame-Order Progress

Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment

Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model

Spectral Rewiring for Exploration, Purification, and Model Merging

PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction