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)

55,141 to 55,200 of 61,428

When Background Matters: Breaking Medical Vision Language Models by Transferable Attack
Akash Ghosh, Subhadip Baidya, Sriparna Saha +1
cs.CVarXiv:2604.17318v12026
Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories
Ivan Bercovich, Ivgeni Segal, Kexun Zhang +3
cs.CRcs.AIarXiv:2604.17596v12026
Just Repair: A Minimal Denoising Network for Time Series Anomaly Detection
Kadir-Kaan Özer, René Ebeling, Markus Enzweiler
cs.LGcs.AIarXiv:2604.17388v32026
Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?
Wang Bill Zhu, Miaosen Chai, Shangshang Wang +5
cs.SEcs.CLarXiv:2604.17338v42026
The Continuity Layer: Why Intelligence Needs an Architecture for What It Carries Forward
Samuel Sameer Tanguturi
cs.AIarXiv:2604.17273v12026
UniMesh: Unifying 3D Mesh Understanding and Generation
Peng Huang, Yifeng Chen, Zeyu Zhang +1
cs.CVarXiv:2604.17472v12026
MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation
Szu-Chi Chen, I-Ning Tsai, Yi-Cheng Lin +2
cs.CLcs.AIcs.SDarXiv:2604.17435v12026
LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
Yueyang Ding, HaoPeng Zhang, Rui Dai +4
cs.AIarXiv:2604.17295v12026
On the Transferability of Agricultural Weed Detection Under Cross-Field Distribution Shift
Nikhilesh Prabhakar, Pranuthi Tenali, Wilfredo Abudeye Fernandez +5
cs.CVcs.LGarXiv:2608.21254v12026
Speculative Decoding for Autoregressive Video Generation
Yuezhou Hu, Jintao Zhang
cs.CVcs.AIarXiv:2604.17397v12026
River-LLM: Large Language Model Seamless Exit Based on KV Share
Yingtao Shen, An Zou
cs.CLarXiv:2604.18396v32026
Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs
Samuel G. Balter, Ethan Jerzak, Connor T. Jerzak
cs.CLarXiv:2604.18203v12026
WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models
Xinping Lei, Xinyu Che, Junqi Xiong +16
cs.SEcs.AIarXiv:2604.18224v12026
On the Reliability of Computer Use Agents
Gonzalo Gonzalez-Pumariega, Saaket Agashe, Jiachen Yang +2
cs.AIarXiv:2604.17849v12026
When Can LLMs Learn to Reason with Weak Supervision?
Salman Rahman, Jingyan Shen, Anna Mordvina +3
cs.LGcs.AIarXiv:2604.18574v12026
MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
Shaden Alshammari, Kevin Wen, Abrar Zainal +5
cs.AIcs.DLcs.IRarXiv:2604.18584v22026
ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
Xirui Li, Ming Li, Ion Stoica +2
cs.AIcs.CLarXiv:2604.18543v42026
OpenGame: Open Agentic Coding for Games
Yilei Jiang, Jinyuan Hu, Qianyin Xiao +8
cs.SEarXiv:2604.18394v12026
Mitigating Multimodal Hallucination via Phase-wise Self-reward
Yu Zhang, Chuyang Sun, Kehai Chen +3
cs.CVcs.CLarXiv:2604.17982v12026
Event-triggered Implicit Perturbation for Zeroth-Order Fine-Tuning of Spiking Transformers
Tengteng Lei, Prabodh Katti, Rashi Dutt +5
cs.ARcs.LGcs.NEarXiv:2608.21223v12026
Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks
Rongyuan Tan, Jue Zhang, Zhuozhao Li +3
cs.AIcs.CLarXiv:2604.17761v12026
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
Jiaqi Wang, Haoge Deng, Ting Pan +5
cs.CVcs.LGarXiv:2604.18518v42026
Dual-View Training for Instruction-Following Information Retrieval
Qingcheng Zeng, Puxuan Yu, Aman Mehta +2
cs.IRarXiv:2604.18845v12026
AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation
Wentao Shi, Yu Wang, Yuyang Zhao +8
cs.AIarXiv:2604.18240v12026
LLM Safety From Within: Detecting Harmful Content with Internal Representations
Difan Jiao, Yilun Liu, Ye Yuan +4
cs.AIarXiv:2604.18519v12026
Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey
Yasmin Moslem, John D. Kelleher
cs.NIcs.CLcs.PFarXiv:2603.04445v22026
Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference
Christos Koutsiaris
cs.IRcs.AIcs.CLarXiv:2608.20210v12026
LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction
Jiakai Tang, Runfeng Zhang, Weiqiu Wang +7
cs.IRarXiv:2604.19550v12026
Accurate and scalable exchange-correlation with deep learning
Giulia Luise, Chin-Wei Huang, Thijs Vogels +25
physics.chem-phcs.AIcs.CEarXiv:2506.14665v62025
From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation
Tianlu Xie, Xin Ku, Mingjie Sun +8
cs.IRcs.LGarXiv:2608.21012v12026
CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation
Chenglong Liu, Xin Zhang, Yimeng Zhu +5
cs.GRcs.CVcs.LGarXiv:2608.20803v12026
HP-Edit: A Human-Preference Post-Training Framework for Image Editing
Fan Li, Chonghuinan Wang, Lina Lei +9
cs.CVcs.AIarXiv:2604.19406v12026
Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language
Yi Zhong, Buqiang Xu, Yijun Wang +4
cs.CLcs.AIcs.CVarXiv:2604.19667v22026
Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement
Alessia Milo, Georg Götz, Steinar Guðjónsson +3
eess.AScs.LGphysics.comp-pharXiv:2608.20971v12026
Rethinking Demonstration Unlearning in Imitation Learning for Robotics
Jiazhuo Li, Yu Zhang, Yiming Fei +4
cs.ROcs.LGarXiv:2608.20784v12026
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
Xiangyang Luo, Xiaozhe Xin, Tao Feng +3
cs.CVarXiv:2604.19636v12026
Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data
Tatsuya Amano, Hirozumi Yamaguchi
cs.CYcs.LGarXiv:2608.20830v12026
SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing
Ying Zeng, Miaosen Luo, Guangyuan Li +10
cs.CVarXiv:2604.19587v12026
Learning Prostate Anatomy at Test Time for Cancer Detection in Micro-Ultrasound
Obed Korshie Dzikunu, Mohammad Mahdi Abootorabi, Mohamed Harmanani +7
cs.CVcs.LGarXiv:2608.20557v12026
ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis
Zhengwentai Sun, Keru Zheng, Chenghong Li +7
cs.CVarXiv:2604.19720v12026
CreativeGame:Toward Mechanic-Aware Creative Game Generation
Hongnan Ma, Han Wang, Shenglin Wang +6
cs.AIarXiv:2604.19926v12026
Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning
Xinyun Liu, Zhi Lu, Yu Chen +1
cs.CRcs.LGarXiv:2608.20580v12026
Interpretable Information-Decomposed Brain Graph Learning for fMRI-based Disease Diagnosis
Dengyi Zhao, Zhiheng Zhou, Zihan Wang +2
q-bio.NCcs.LGarXiv:2608.20380v12026
Tadabur: A Large-Scale Quran Audio Dataset
Faisal Alherran
cs.SDcs.AIarXiv:2604.18932v12026
Keep Your Friends Close, and the Right Neighbours Closer: Disaster-Conditioned Kernel-Regularized Graph Attention for Building Damage Classification
Fuad Hasan, Chul Min Yeum
cs.CVcs.LGarXiv:2608.20548v12026
Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
Hardy Chen, Nancy Lau, Haoqin Tu +8
cs.CLarXiv:2604.20200v12026
EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training
Yiyang Du, Zhanqiu Guo, Xin Ye +2
cs.CVcs.AIcs.CLarXiv:2604.20012v12026
Rethinking Expressivity and Efficiency in Test-Time Training
Zeyun Zhong, Joya Chen, Manuel Martin +3
cs.LGarXiv:2608.21308v12026
Cortex 2.0: Grounding World Models in Real-World Industrial Deployment
Adriana Aida, Walid Amer, Katarina Bankovic +25
cs.ROcs.AIarXiv:2604.20246v12026
SWE-chat: Coding Agent Interactions From Real Users in the Wild
Joachim Baumann, Vishakh Padmakumar, Xiang Li +3
cs.AIcs.CYcs.SEarXiv:2604.20779v12026
Asymmetric Capacity Allocation in Self-Refinement Pipelines
Zhuoyi Yang, Ian G. Harris, Salar Hashemitaheri +7
cs.LGarXiv:2608.21345v12026
What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
Xinhao Zhang, Xi Chen, François Portet +1
cs.CLcs.NEarXiv:2604.19440v12026
Time-Aware Tranformer-Based Prediction Model for AECOPD
Weihao Qu, Ling Zheng, Dongyang Wang +2
cs.LGarXiv:2608.21324v12026
Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates
Hui Wei, Licai Sun, Guoying Zhao
cs.CVcs.LGarXiv:2608.21160v12026
RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models
Yusuf Çelebi, Yağız Asker, Özay Ezerceli +4
cs.LGcs.AIcs.CLarXiv:2604.19321v12026
AudioWorldSim: Realistic Binaural Audio Datasets For World Models
Luis Vitor Zerkowski, Luiz Velho
cs.SDcs.LGarXiv:2608.21075v12026
ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation
Zhiqin Yang, Zhenyuan Zhang, Xianzhang Jia +4
cs.AIarXiv:2604.19211v12026
PlayCoder: Making LLM-Generated GUI Code Playable
Zhiyuan Peng, Wei Tao, Xin Yin +3
cs.SEarXiv:2604.19742v12026
Sharing the Control Authority Between Deep Reinforcement Learning and Model Predictive Control: Application to Multi-Class Transportation Networks
Giray Onur, Azita Dabiri, Bart De Schutter
eess.SYcs.LGarXiv:2608.20858v12026
ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning
Xianming Li, Zongxi Li, Tsz-fung Andrew Lee +3
cs.CLcs.AIarXiv:2604.19254v12026

Every paper with a summary

When Background Matters: Breaking Medical Vision Language Models by Transferable Attack

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

Just Repair: A Minimal Denoising Network for Time Series Anomaly Detection

Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?

The Continuity Layer: Why Intelligence Needs an Architecture for What It Carries Forward

UniMesh: Unifying 3D Mesh Understanding and Generation

MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation

LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics

On the Transferability of Agricultural Weed Detection Under Cross-Field Distribution Shift

Speculative Decoding for Autoregressive Video Generation

River-LLM: Large Language Model Seamless Exit Based on KV Share

Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs

WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models

On the Reliability of Computer Use Agents

When Can LLMs Learn to Reason with Weak Supervision?

MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval

ClawEnvKit: Automatic Environment Generation for Claw-Like Agents

OpenGame: Open Agentic Coding for Games

Mitigating Multimodal Hallucination via Phase-wise Self-reward

Event-triggered Implicit Perturbation for Zeroth-Order Fine-Tuning of Spiking Transformers

Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks

UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models

Dual-View Training for Instruction-Following Information Retrieval

AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation

LLM Safety From Within: Detecting Harmful Content with Internal Representations

Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey

Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference

LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction

Accurate and scalable exchange-correlation with deep learning

From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation

CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation

HP-Edit: A Human-Preference Post-Training Framework for Image Editing

Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language

Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement

Rethinking Demonstration Unlearning in Imitation Learning for Robotics

CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation

Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data

SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing

Learning Prostate Anatomy at Test Time for Cancer Detection in Micro-Ultrasound

ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis

CreativeGame:Toward Mechanic-Aware Creative Game Generation

Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning

Interpretable Information-Decomposed Brain Graph Learning for fMRI-based Disease Diagnosis

Tadabur: A Large-Scale Quran Audio Dataset

Keep Your Friends Close, and the Right Neighbours Closer: Disaster-Conditioned Kernel-Regularized Graph Attention for Building Damage Classification

Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows

EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training

Rethinking Expressivity and Efficiency in Test-Time Training

Cortex 2.0: Grounding World Models in Real-World Industrial Deployment

SWE-chat: Coding Agent Interactions From Real Users in the Wild

Asymmetric Capacity Allocation in Self-Refinement Pipelines

What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search

Time-Aware Tranformer-Based Prediction Model for AECOPD

Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates

RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models

AudioWorldSim: Realistic Binaural Audio Datasets For World Models

ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation

PlayCoder: Making LLM-Generated GUI Code Playable

Sharing the Control Authority Between Deep Reinforcement Learning and Model Predictive Control: Application to Multi-Class Transportation Networks

ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning