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)

54,541 to 54,600 of 61,270

Deep Packet: A Novel Approach For Encrypted Traffic Classification Using Deep Learning
Mohammad Lotfollahi, Ramin Shirali Hossein Zade, Mahdi Jafari Siavoshani +1
cs.LGcs.CRcs.NIarXiv:1709.02656v32017
TS2Vec: Towards Universal Representation of Time Series
Zhihan Yue, Yujing Wang, Juanyong Duan +4
cs.LGcs.AIarXiv:2106.10466v42021
Dynamic Filter Networks
Bert De Brabandere, Xu Jia, Tinne Tuytelaars +1
cs.LGcs.CVarXiv:1605.09673v22016
Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation
Shengze Wang, Michael Stengel, Tianye Li +5
cs.CVarXiv:2608.20534v12026
RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
Yinpei Dai, Hongze Fu, Jayjun Lee +6
cs.ROcs.AIarXiv:2603.04639v32026
Snapshot Ensembles: Train 1, get M for free
Gao Huang, Yixuan Li, Geoff Pleiss +3
cs.LGarXiv:1704.00109v12017
A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
Mingxuan Du, Benfeng Xu, Chiwei Zhu +4
cs.CLarXiv:2602.03442v12026
Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
Miao Xiong, Zhiyuan Hu, Xinyang Lu +4
cs.CLarXiv:2306.13063v22023
LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation
Ahmadreza Jeddi, Marco Ciccone, Babak Taati
cs.CLarXiv:2602.11451v12026
FAST-LIO: A Fast, Robust LiDAR-inertial Odometry Package by Tightly-Coupled Iterated Kalman Filter
Wei Xu, Fu Zhang
cs.ROarXiv:2010.08196v32020
Natural-Language Agent Harnesses
Linyue Pan, Lexiao Zou, Shuo Guo +2
cs.CLcs.AIarXiv:2603.25723v22026
Kimi K2.5: Visual Agentic Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +334
cs.CLcs.AIcs.LGarXiv:2602.02276v22026
Summaries:한국어
Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
Yuqian Fu, Haohuan Huang, Kaiwen Jiang +4
cs.LGcs.AIcs.CLarXiv:2603.25562v22026
Meta-Harness: End-to-End Optimization of Model Harnesses
Yoonho Lee, Roshen Nair, Qizheng Zhang +3
cs.AIarXiv:2603.28052v12026
MOVA: Towards Scalable and Synchronized Video-Audio Generation
SII-OpenMOSS Team, :, Donghua Yu +39
cs.CVcs.SDarXiv:2602.08794v22026
Summaries:한국어
Towards a Science of AI Agent Reliability
Stephan Rabanser, Sayash Kapoor, Peter Kirgis +3
cs.AIcs.CYcs.LGarXiv:2602.16666v32026
RoboBrain 2.5: Depth in Sight, Time in Mind
Huajie Tan, Enshen Zhou, Zhiyu Li +32
cs.ROarXiv:2601.14352v12026
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
Shengbang Tong, Boyang Zheng, Ziteng Wang +7
cs.CVarXiv:2601.16208v12026
Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
Wenkai Yang, Weijie Liu, Ruobing Xie +3
cs.LGcs.AIcs.CLarXiv:2602.12125v22026
Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
George Ling, Shanshan Zhong, Richard Huang
cs.SEcs.SIarXiv:2602.08004v12026
DeepSeek-OCR 2: Visual Causal Flow
Haoran Wei, Yaofeng Sun, Yukun Li
cs.CVarXiv:2601.20552v12026
PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
Cheng Cui, Ting Sun, Suyin Liang +12
cs.CVarXiv:2601.21957v22026
LLaDA2.1: Speeding Up Text Diffusion via Token Editing
Tiwei Bie, Maosong Cao, Xiang Cao +47
cs.LGcs.AIarXiv:2602.08676v32026
Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation
Hongzhou Zhu, Min Zhao, Guande He +3
cs.CVarXiv:2602.02214v52026
Self-Distillation Enables Continual Learning
Idan Shenfeld, Mehul Damani, Jonas Hübotter +1
cs.LGarXiv:2601.19897v22026
Summaries:한국어
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Xiangyi Li, Yimin Liu, Wenbo Chen +75
cs.AIarXiv:2602.12670v42026
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Jingwei Ni, Yihao Liu, Xinpeng Liu +7
cs.AIarXiv:2603.25158v52026
GigaWorld-Policy: An Efficient Action-Centered World--Action Model
Angen Ye, Boyuan Wang, Chaojun Ni +21
cs.CVarXiv:2603.17240v22026
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Christopher Clark, Jieyu Zhang, Zixian Ma +18
cs.CVcs.AIarXiv:2601.10611v42026
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
Yi Liu, Weizhe Wang, Ruitao Feng +5
cs.CRcs.AIcs.CLarXiv:2601.10338v12026
DFlash: Block Diffusion for Flash Speculative Decoding
Jian Chen, Yesheng Liang, Zhijian Liu
cs.CLarXiv:2602.06036v22026
Qwen3-TTS Technical Report
Hangrui Hu, Xinfa Zhu, Ting He +13
cs.SDcs.CLeess.ASarXiv:2601.15621v12026
Summaries:简体中文
Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
Hao Luo, Ye Wang, Wanpeng Zhang +9
cs.ROarXiv:2601.12993v12026
Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics
Junqi Liu, Zihao Zhou, Zekai Zhu +10
cs.AIarXiv:2601.14027v12026
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Peng Xia, Jianwen Chen, Hanyang Wang +10
cs.LGarXiv:2602.08234v12026
CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
Hejian Sang, Yuanda Xu, Zhengze Zhou +3
cs.LGarXiv:2603.05433v72026
Causal World Modeling for Robot Control
Lin Li, Qihang Zhang, Yiming Luo +9
cs.CVcs.ROarXiv:2601.21998v22026
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Weinan Dai, Hanlin Wu, Qiying Yu +13
cs.LGcs.AIarXiv:2602.24286v12026
SkillNet: Create, Evaluate, and Connect AI Skills
Yuan Liang, Ruobin Zhong, Haoming Xu +47
cs.AIcs.CLcs.CVarXiv:2603.04448v22026
CL-bench: A Benchmark for Context Learning
Shihan Dou, Ming Zhang, Zhangyue Yin +24
cs.CLarXiv:2602.03587v12026
One-step Latent-free Image Generation with Pixel Mean Flows
Yiyang Lu, Susie Lu, Qiao Sun +6
cs.CVarXiv:2601.22158v32026
Helios: Real Real-Time Long Video Generation Model
Shenghai Yuan, Yuanyang Yin, Zongjian Li +3
cs.CVarXiv:2603.04379v12026
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
Jingwen Sun, Wenyao Zhang, Zekun Qi +6
cs.ROcs.CVarXiv:2602.10098v22026
Ministral 3
Alexander H. Liu, Kartik Khandelwal, Sandeep Subramanian +117
cs.CLarXiv:2601.08584v12026
Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
Haiyang Xu, Xi Zhang, Haowei Liu +16
cs.AIcs.CLarXiv:2602.16855v12026
OpenClaw-RL: Train Any Agent Simply by Talking
Yinjie Wang, Xuyang Chen, Xiaolong Jin +2
cs.CLcs.AIcs.CVarXiv:2603.10165v22026
Attention Residuals
Kimi Team, Guangyu Chen, Yu Zhang +34
cs.CLarXiv:2603.15031v12026
Hydra-0: Action Flow for Generalist World Modeling and Control
Hongyu Li, Bowen Wen, Xinghao Zhu +8
cs.ROarXiv:2608.18077v12026
ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
Yandan Yang, Shuang Zeng, Tong Lin +11
cs.CVcs.CLcs.ROarXiv:2602.11236v22026
A Pragmatic VLA Foundation Model
Wei Wu, Fan Lu, Yunnan Wang +22
cs.ROcs.CVarXiv:2601.18692v42026
The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
Christina Lu, Jack Gallagher, Jonathan Michala +2
cs.CLarXiv:2601.10387v12026
SAM 3D Body: Robust Full-Body Human Mesh Recovery
Xitong Yang, Devansh Kukreja, Don Pinkus +11
cs.CVarXiv:2602.15989v12026
MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
Haozhen Zhang, Quanyu Long, Jianzhu Bao +4
cs.CLcs.AIcs.LGarXiv:2602.02474v22026
Qwen3-Coder-Next Technical Report
Ruisheng Cao, Mouxiang Chen, Jiawei Chen +17
cs.CLarXiv:2603.00729v12026
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
Tingxu Han, Yi Zhang, Wei Song +4
cs.SEcs.AIarXiv:2603.15401v12026
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
Lorenzo Mur-Labadia, Matthew Muckley, Amir Bar +6
cs.CVarXiv:2603.14482v32026
Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
Moo Jin Kim, Yihuai Gao, Tsung-Yi Lin +8
cs.AIcs.ROarXiv:2601.16163v12026
Advancing Open-source World Models
Robbyant Team, Zelin Gao, Qiuyu Wang +21
cs.CVarXiv:2601.20540v12026
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
Shenyuan Gao, William Liang, Kaiyuan Zheng +27
cs.ROcs.AIcs.CVarXiv:2602.06949v12026
World Action Models are Zero-shot Policies
Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng +33
cs.ROcs.CVcs.LGarXiv:2602.15922v12026

Every paper with a summary

Deep Packet: A Novel Approach For Encrypted Traffic Classification Using Deep Learning

TS2Vec: Towards Universal Representation of Time Series

Dynamic Filter Networks

Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation

RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies

Snapshot Ensembles: Train 1, get M for free

A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces

Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation

FAST-LIO: A Fast, Robust LiDAR-inertial Odometry Package by Tightly-Coupled Iterated Kalman Filter

Natural-Language Agent Harnesses

Kimi K2.5: Visual Agentic Intelligence

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes

Meta-Harness: End-to-End Optimization of Model Harnesses

MOVA: Towards Scalable and Synchronized Video-Audio Generation

Towards a Science of AI Agent Reliability

RoboBrain 2.5: Depth in Sight, Time in Mind

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality

DeepSeek-OCR 2: Visual Causal Flow

PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

LLaDA2.1: Speeding Up Text Diffusion via Token Editing

Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

Self-Distillation Enables Continual Learning

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

GigaWorld-Policy: An Efficient Action-Centered World--Action Model

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

DFlash: Block Diffusion for Flash Speculative Decoding

Qwen3-TTS Technical Report

Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization

Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

CRISP: Compressed Reasoning via Iterative Self-Policy Distillation

Causal World Modeling for Robot Control

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

SkillNet: Create, Evaluate, and Connect AI Skills

CL-bench: A Benchmark for Context Learning

One-step Latent-free Image Generation with Pixel Mean Flows

Helios: Real Real-Time Long Video Generation Model

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model

Ministral 3

Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents

OpenClaw-RL: Train Any Agent Simply by Talking

Attention Residuals

Hydra-0: Action Flow for Generalist World Modeling and Control

ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning

A Pragmatic VLA Foundation Model

The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models

SAM 3D Body: Robust Full-Body Human Mesh Recovery

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

Qwen3-Coder-Next Technical Report

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

Advancing Open-source World Models

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

World Action Models are Zero-shot Policies