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)

35,401 to 35,460 of 119,999

Protecting Language Models Against Unauthorized Distillation through Trace Rewriting
Xinhang Ma, William Yeoh, Ning Zhang +1
cs.AIcs.CLarXiv:2602.15143v22026
An 8-flow theorem for signed graphs
Rong Luo, Edita Máčajová, Martin Škoviera +1
math.COarXiv:2402.12883v12024
Discrete Audio Tokens: More Than a Survey!
Pooneh Mousavi, Gallil Maimon, Adel Moumen +18
cs.SDcs.AIcs.CLarXiv:2506.10274v32025
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
Zhenxin Ai, Haiyun He
cs.CRcs.AIarXiv:2605.10977v22026
Bounds on the Posterior-to-Prior Ratios for Inclusion Belief under Bounded Differential Privacy
Jan Reiter Sørensen, Heidi Søgaard Christensen, Rasmus Rask Kragh Jørgensen +1
math.STcs.CRarXiv:2608.30473v12026
Interactive Error Correction in Implicative Theories
Sergei O. Kuznetsov, Artem Revenko
cs.AIarXiv:1410.5215v12014
Learning Generalizable Behaviors for Terminal Agents
Yihang Yao, Bo Pang, Xuan Phi Nguyen +3
cs.LGarXiv:2608.22631v12026
SPRITE: From Static Mockups to Engine-Ready Game UI
Yunshu Bai, RuiHao Li, Hao Zhang +3
cs.HCcs.AIarXiv:2604.18591v12026
Gaussian Material Fields for Volumetric Multi-Energy CT Decomposition
Jian Lin, Jiancheng Fang, Hongming Shan +3
cs.CVarXiv:2610.09492v12026
DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale
Samyam Rajbhandari, Conglong Li, Zhewei Yao +5
cs.LGcs.AIcs.DCarXiv:2201.05596v22022
Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access
Bhuwan Dhingra, Lihong Li, Xiujun Li +4
cs.CLcs.LGarXiv:1609.00777v32016
Function-Correcting Lee-distance Codes for Symbol-Pair Read Channels
Hareesh K., B. Sundar Rajan
cs.ITmath.ITarXiv:2610.09491v12026
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
Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses
Tianyi She, Jiawei Liu, Weifeng Liu +3
cs.CVcs.CRarXiv:2610.08417v12026
Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models
Jinbin Bai, Yixuan Li, Yuchen Zhu +8
cs.LGarXiv:2602.01842v32026
MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences
Shijian Wang, Jiarui Jin, Runhao Fu +11
cs.CVarXiv:2603.27813v12026
Pattern-Coupled Sparse Bayesian Learning for Recovery of Block-Sparse Signals
Jun Fang, Yanning Shen, Hongbin Li +1
cs.ITcs.LGstat.MLarXiv:1311.2150v12013
Differentially Private Iterative Synchronous Consensus
Zhenqi Huang, Sayan Mitra, Geir Dullerud
cs.CRcs.DCeess.SYarXiv:1207.4262v22012
Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
Cristian McGee, El Houcine Bergou, Aritra Dutta
cs.LGmath.OCarXiv:2610.02190v12026
MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads
Meng'en Qin, Junye Chen, Jucheng Liu +3
cs.CVcs.CLarXiv:2609.09206v12026
$τ_0$-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation
Xiaowei Cai, Yunuo Cai, Bingao Chen +36
cs.ROarXiv:2608.16885v12026
Geometry-Based Metrics for Early-Stage Hull-Form Producibility Screening
Andrea Serani, Kevin Maki
cs.CEcs.CGarXiv:2609.27544v12026
RoboHarn-Evo: Evolving Hierarchical Physical Knowledge for Self-Improving Robotic Manipulation
Shifeng Bao, Fanding Huang, Yihan Lin +7
cs.ROarXiv:2609.37583v22026
Mean field games as a tool for AI safety: a worked example from the July 2026 Hugging Face incident
P. Jameson Graber
math.OCcs.AIcs.GTarXiv:2610.00902v12026
When Can One Obtain Certificates of Optimality Using Positivstellensaetze?
Nayoon Kim, Allen Gehret, Shenyuan Ma +1
cs.AIarXiv:2609.08736v12026
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
Xianpeng Liu, Nan Xue, Tianfu Wu
cs.CVarXiv:2112.04628v12021
Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use
Kunvar Thaman
cs.LGcs.AIarXiv:2605.02964v12026
Numerical investigation of a homogenized model with effective interface conditions for Stokes flow through porous membranes
Jonas Knoch, Pietro Italiano, Markus Gahn +2
math.NAcs.NAarXiv:2609.37068v22026
Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification
Minu Kim, Jihwan Lee, David R. Mortensen +1
eess.AScs.CLcs.SDarXiv:2610.09486v12026
Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization
Xuekang Zhu, Kaiwen Feng, Ruifeng Wang +10
cs.CVarXiv:2610.07916v12026
Learning Sample-wise Rank-aware Interpolation Weights for Composed Visual Data Retrieval
Boseung Jeong, Taegyu Park, Donghyeon Kwon +2
cs.CVarXiv:2608.22500v12026
Mapping the Emerging Social Science of Large Language Models
Yi Yang, Xiao Jia, Zeyun Dong +2
cs.CYcs.AIcs.CLarXiv:2609.07598v12026
Polynomial Lower Bounds for Distributed Graph Sketching with Tiny Error: Connectivity and Spanning Tree Construction
Peter Robinson, Ming Ming Tan
cs.DScs.DCarXiv:2609.05795v12026
Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents
Zeyu Zhang, Dingyi Rong, Zijian Chen +3
cs.CVarXiv:2609.27461v12026
Higher-Order Molecular Grammars for Generative and Foundation Models in Chemistry
Yiming Huang, Yujie Zeng, Vijay Prakash Dwivedi +4
cs.LGcs.AIarXiv:2610.02186v12026
SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery
Yezhen Cong, Samar Khanna, Chenlin Meng +6
cs.CVcs.AIarXiv:2207.08051v32022
Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads
Jingjie Ning, Xueqi Li, Yibo Kong
cs.IRarXiv:2610.05034v12026
Protein Language Models and Structure Prediction: Connection and Progression
Bozhen Hu, Jun Xia, Jiangbin Zheng +4
q-bio.QMcs.AIcs.LGarXiv:2211.16742v12022
From Parity to Preference-based Notions of Fairness in Classification
Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez +2
stat.MLcs.LGarXiv:1707.00010v22017
VizIt: A multi-view framework for exploring single-cell, spatial, and genetic data online
Chenhang Christopher Zhang, Yanqing Lou, Jie Yuan +8
cs.IRq-bio.GNarXiv:2609.04658v12026
MAGiDiff: Sampling the Photospheric Vector Field from UV/EUV Filtergrams
Ruoyu Wang, David Fouhey
astro-ph.SRastro-ph.IMcs.CVarXiv:2609.40043v12026
Long Horizon Transformer Quantile Fault Prediction for Multi Site Industrial Predictive Maintenance
David J Poland, Daniele Ravi, Na Helian
cs.AIarXiv:2609.04840v12026
Quantum Query Complexity for List Search
Niranka Banerjee, Akinori Kawachi
quant-phcs.DSarXiv:2609.38736v12026
Combined High-Dimensional and Reduced-Order Modeling Based on an Iterative Domain Decomposition Method
Taiji Saito, Tomoshi Miyamura, Yasunori Yusa
math.NAarXiv:2608.25567v12026
The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI Operators
Tarfah Alrashed, Fatma Ozcan, Per Jacobsson +2
cs.DBcs.AIarXiv:2609.21133v12026
UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones
Daniela Micucci, Marco Mobilio, Paolo Napoletano
cs.CVarXiv:1611.07688v52016
AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science
An Luo, Jin Du, Xun Xian +12
cs.LGcs.AIstat.MEarXiv:2603.19005v32026
Aerial Reliable Collaborative Communications for Terrestrial Mobile Users via Evolutionary Multi-Objective Deep Reinforcement Learning
Geng Sun, Jian Xiao, Jiahui Li +4
cs.NEarXiv:2502.05824v12025
Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)
Harshdeep Singh, Yurui Zhu, Giovanni Colavizza +1
cs.AIcs.LGarXiv:2609.11569v12026
Unsupervised Multi-Scale Gromov-Wasserstein Hypergraph Alignment
Lutz Oettershagen, Honglian Wang, Aristides Gionis
cs.LGcs.SIarXiv:2608.29635v12026
Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression Target
Du Cheng, Junyu Lu, Jingfan Zhang +3
cs.LGarXiv:2610.12830v12026
Message Passing Algorithms for Compressed Sensing: I. Motivation and Construction
David L. Donoho, Arian Maleki, Andrea Montanari
cs.ITarXiv:0911.4219v12009
Proxy reliance in large language model decisions is uncalibrated to predictive evidence
Zengqing Wu, Chuan Xiao
cs.AIcs.CLcs.CYarXiv:2608.22887v12026
ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs
Songyuan Li, Ahmed M. Abdelmoniem, Shiqiang Wang
cs.AIcs.MAarXiv:2608.25992v12026
Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation
Yugu Li, Zehong Cao, Peizhen Li +3
cs.AIarXiv:2609.34848v12026
High-Dimensional Simulation-Based Inference in Latent Spaces
Lars Kühmichel, Stefan T. Radev, Bhanu Prasanna Koppolu +3
cs.LGstat.MLarXiv:2609.37381v12026
CETalk: Continuous Valence-Arousal Control for Audio-Driven 3D Talking Head Generation
Peng Jia, Li Dai, Zhen Xiao +2
cs.CVcs.AIarXiv:2608.15110v12026
StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
Yuhan Song, Linhao Zhang, Chuhan Wu +4
cs.CLcs.SDarXiv:2509.22220v22025
Scalable Multi-Task Inverse Reinforcement Learning
Allen Tran, Jia Wan, Nathan Kallus +1
cs.LGstat.MLarXiv:2610.00758v12026
SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection
Xuwei Tan, Yao Ma, Xueru Zhang
cs.LGcs.CRarXiv:2609.27287v12026

Every paper with a summary

Protecting Language Models Against Unauthorized Distillation through Trace Rewriting

An 8-flow theorem for signed graphs

Discrete Audio Tokens: More Than a Survey!

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

Bounds on the Posterior-to-Prior Ratios for Inclusion Belief under Bounded Differential Privacy

Interactive Error Correction in Implicative Theories

Learning Generalizable Behaviors for Terminal Agents

SPRITE: From Static Mockups to Engine-Ready Game UI

Gaussian Material Fields for Volumetric Multi-Energy CT Decomposition

DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale

Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

Function-Correcting Lee-distance Codes for Symbol-Pair Read Channels

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

Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses

Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models

MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences

Pattern-Coupled Sparse Bayesian Learning for Recovery of Block-Sparse Signals

Differentially Private Iterative Synchronous Consensus

Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning

MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads

$τ_0$-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation

Geometry-Based Metrics for Early-Stage Hull-Form Producibility Screening

RoboHarn-Evo: Evolving Hierarchical Physical Knowledge for Self-Improving Robotic Manipulation

Mean field games as a tool for AI safety: a worked example from the July 2026 Hugging Face incident

When Can One Obtain Certificates of Optimality Using Positivstellensaetze?

Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection

Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use

Numerical investigation of a homogenized model with effective interface conditions for Stokes flow through porous membranes

Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification

Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization

Learning Sample-wise Rank-aware Interpolation Weights for Composed Visual Data Retrieval

Mapping the Emerging Social Science of Large Language Models

Polynomial Lower Bounds for Distributed Graph Sketching with Tiny Error: Connectivity and Spanning Tree Construction

Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents

Higher-Order Molecular Grammars for Generative and Foundation Models in Chemistry

SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery

Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads

Protein Language Models and Structure Prediction: Connection and Progression

From Parity to Preference-based Notions of Fairness in Classification

VizIt: A multi-view framework for exploring single-cell, spatial, and genetic data online

MAGiDiff: Sampling the Photospheric Vector Field from UV/EUV Filtergrams

Long Horizon Transformer Quantile Fault Prediction for Multi Site Industrial Predictive Maintenance

Quantum Query Complexity for List Search

Combined High-Dimensional and Reduced-Order Modeling Based on an Iterative Domain Decomposition Method

The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI Operators

UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones

AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science

Aerial Reliable Collaborative Communications for Terrestrial Mobile Users via Evolutionary Multi-Objective Deep Reinforcement Learning

Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)

Unsupervised Multi-Scale Gromov-Wasserstein Hypergraph Alignment

Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression Target

Message Passing Algorithms for Compressed Sensing: I. Motivation and Construction

Proxy reliance in large language model decisions is uncalibrated to predictive evidence

ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs

Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation

High-Dimensional Simulation-Based Inference in Latent Spaces

CETalk: Continuous Valence-Arousal Control for Audio-Driven 3D Talking Head Generation

StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs

Scalable Multi-Task Inverse Reinforcement Learning

SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection