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)

90,781 to 90,840 of 102,008

Redakto - The Incognito Tab for LLMs
Saurav Kumar Saha, Tom Röhr, Felix Bießmann
cs.AIcs.CLcs.CRarXiv:2608.18260v12026
Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning
Haodong Li, Shaoteng Liu, Tianyu Wang +7
cs.CVarXiv:2608.09926v12026
Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda
Wei Lin, Tao Zhou, Zhaofei Xie +1
cs.AIcs.SEarXiv:2608.21107v12026
Pre-training Visual Dexterity in Simulation
Sarthak Kamat, Adam Rashid, Satvik Sharma +4
cs.ROcs.AIcs.CVarXiv:2608.15917v12026
Safety Alignment Illusion: The Cross-Lingual Safety Gap in LLMs
Namya Bhatnagar
cs.AIcs.CLcs.CYarXiv:2608.18131v12026
GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation
Ming Qian, Zijian Wang, Minchao Sun +5
cs.CVarXiv:2608.17988v12026
PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection
Md. Shakhoyat Rahman Shujon, MD Jahid Hasan Jim, Md. Milon Islam +2
cs.CLcs.LGarXiv:2607.04690v12026
TokenPowerSandbox: Evidence-Gated CPU-First Screening for Energy-Aware LLM Serving
Chenxu Niu
cs.ARcs.AIcs.DCarXiv:2608.18149v12026
Investigating Forecast Proficiency of Hurricane-Induced Compound Flooding With a Discontinuous Galerkin Shallow Water Equation Solver
Matthew Scarborough, Chayanon Wichitrnithed, Shintaro Bunya +4
cs.CEarXiv:2608.27778v12026
Entity tracking emerges in sub-billion parameter language models and exceeds human performance in naturalistic narratives
Karolina Drożdż, Micha Heilbron
cs.CLarXiv:2608.18083v12026
OOD Detection for EEG-based Machine Learning in High-Risk Environments
Philipp Bomatter, Henry Gouk
cs.LGarXiv:2608.17620v12026
FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model
Jiaqi Li, Chaoren Wang, Xiaohai Tian +9
cs.SDeess.ASarXiv:2606.31247v12026
Beyond What Meets the Eye: Unveiling Situational Illusions for Multimodal Large Language Models
Zhiming Yang, Zhuoxi Xiong, Donglin Zhou +3
cs.AIcs.CLcs.CVarXiv:2608.22232v12026
Sparse Token Routing in Efficient Transformers
Sai Krishna Arthanari, JaeHyeong Chang, Chengzhe Sun +1
cs.CLarXiv:2608.20632v12026
From Entity Mentions to Tone: An LLM-Based Pipeline for Media Bias Analysis
Klesti Hoxha, Olti Qirici
cs.CLarXiv:2608.17454v12026
TRACE-BN: Transferring Bangla-English Tutoring Behavior to a Sub-1B Offline Language Model
Khan Raiyan Ibne Reza, Sanjana Aktar Maria, Mohammad Tushar Abdullah +2
cs.CLarXiv:2608.15223v12026
TRACE: Artifact-Robust Statistical Shape Modeling from Imperfect Surface Scans - A Case Study in Craniosynostosis 3D Photography
Sanjay Bhandari, Nawazish Khan, Alzbeta Novotna +7
cs.CVcs.AIarXiv:2608.22131v12026
What Does CLIP Learn for Regional Geolocalization? Probing Visual Cues and Scene Configuration After Adaptation
Changyu Lee, Yeonsoo Park, Abdullah Alfarrarjeh +1
cs.AIcs.CEcs.CVarXiv:2608.21761v12026
A Pilot Study of Autocompleting Tokenizers
Samuel Wexler, Mark Hopkins
cs.CLarXiv:2608.15080v12026
Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents
Minbyul Jeong
cs.CLarXiv:2606.27595v12026
ARGUS: Theory-of-Mind Guided Argument Generation with Strategy-Aware Planning and Knowledge Grounding
Zhe Hu
cs.CLarXiv:2608.20405v12026
CRS-Bench: A Reference-Relative Reliability Benchmark for Medical Image Encoders
Xingtao Lin, Hangqi Ren, Caiwan Sun +1
eess.IVcs.AIcs.CVarXiv:2608.22059v12026
Poly-InstructTTS: Learning In-the-Wild Expressive Speech Synthesis from Open-Ended Instructions
Junhui Zhang, Qianhui Xu, Qingxiang Guo +4
cs.CLcs.AIarXiv:2608.20387v12026
ViPO: Visual Preference Optimization at Scale
Ming Li, Jie Wu, Justin Cui +3
cs.CVcs.AIarXiv:2604.24953v22026
One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications
Szu-Wei Fu, Rong Chao, Xuesong Yang +4
cs.SDarXiv:2606.25621v22026
The Divergence Hypothesis: Unmasking Lexical Interference and Label Bias in Mental Health NLP
Moustafa Yehia Hassan
cs.CLcs.AIarXiv:2608.20353v12026
Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference
Christos Koutsiaris
cs.IRcs.AIcs.CLarXiv:2608.20210v12026
TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection
Su Wang, Yaochen Li, Min Yang +3
cs.CVcs.AIcs.ROarXiv:2608.27282v12026
AISA: AI Safety Assistant Framework for Continuous Improvement of Highway Construction
Mason Smetana, Trevor Neece, Lev Khazanovich
cs.CLarXiv:2608.17184v12026
Summaries:한국어
Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation
Siyuan Liu, Jinyang Wu
cs.AIcs.CLcs.CVarXiv:2606.09131v12026
Prediction of Prediction (PoP): Inter-Layer Activation Fusion for Single-Pass Hallucination Detection in Large Language Models
Himal Badu
cs.CLarXiv:2608.27165v12026
A Comprehensive Survey of Wireless Foundation Models for AI-Native 6G Networks
Naveed Khan, Besan Al Sbeihi, Maryam Alshehhi +1
cs.AIcs.NIeess.SParXiv:2608.14694v12026
A Few Cases Are All You Need: An Empirical Study of Annotation-Efficient LoRA Fine-Tuning of MedSAM3
Sachin Dudda Nagaraju, Bendik Skarre Abrahamsen, Ashkan Moradi +1
cs.CVcs.AIarXiv:2608.18731v12026
FedPref: Federated Preference Learning for Structured Radiology Report Extraction
Flint Xiaofeng Fan, Cheston Tan, Yew-Soon Ong +1
cs.AIcs.LGarXiv:2608.16971v12026
Software Frameworks for Explainable AI in Time Series Classification: A Systematic Review
Louis Peter, Nils Gumpfer, Jana Fischer +2
cs.AIarXiv:2608.21449v12026
A-CPES: A Reference Framework for Agentic AI in Cyber-Physical Energy Systems
Xiaoyu Zhang, Qiuye Sun, Jiachen Xu +2
cs.AIarXiv:2608.22672v12026
Effective Personalized AI Tutors via LLM-Guided Reinforcement Learning
Angel Tsai-Hsuan Chung, Botong Zhang, Ling-Chieh Kung +2
cs.CYcs.AIarXiv:2608.16907v12026
Do Not Copy/Paste: Soft Barriers for Copying in AI-Assisted Programming
Iyiola E. Olatunji, Alberick Euraste Djire, Jacques Klein +1
cs.SEcs.AIarXiv:2608.22638v12026
When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents
Jiawei Liu, Jiacheng Guo, Tian Zhang +7
cs.ROcs.AIarXiv:2608.16806v12026
FrenchNews-7: Benchmarking Cross-Publisher French News Editorial Desk Classification
Amr Sobhy
cs.CLarXiv:2608.18097v12026
Beyond Two Bytes per Letter: Tokenization Overhead in Cyrillic AI Systems
Ivan Dobrovolskyi
cs.CLcs.AIarXiv:2608.21384v12026
Reviewing Model Collapse and Countermeasures
Xihao Xie, Beichen Hu
cs.AIcs.LGarXiv:2608.21366v12026
How Much Do Legal RAG Systems Still Hallucinate?
Souvick Das, Sallam Abualhaija, Domenico Bianculli
cs.CLcs.AIarXiv:2608.14210v12026
H$^2$SD: Hybrid Hindsight Self-Distillation
Qiye Cai, Yichuan Ma, Peiji Li +6
cs.LGcs.CLarXiv:2607.18955v42026
Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge
Kexin Shi, Renhe Sun, Yuge Huang +4
cs.CLarXiv:2608.14150v12026
Decoupling Planning and Control for Instructable Agents
Zineng Tang, Kelsey R. Allen, Sjoerd van Steenkiste +2
cs.AIcs.CLcs.MAarXiv:2608.26788v12026
Data-Driven Reconstruction of Spatially Resolved Electron and Ion Energy Distributions from Macroscopic Plasma Quantities with Deep Neural Networks
Libin Varghese, Kaushik Prajapati, Bhaskar Chaudhury
physics.plasm-phcs.LGphysics.comp-pharXiv:2608.16519v12026
When Adaptation Hurts: Connecting Representational Drift to OOD Failures in MedSAM Fine-Tuning
Marko Haralović, Sounic Akkaraju, Carlo Baretta +2
cs.CVarXiv:2608.21300v12026
Benchmarking Patent Drafting from Inventor-Style Disclosures
Lekang Jiang, Wenjun Sun, Stephan Goetz
cs.CLarXiv:2608.21249v12026
From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sector
Camilla Dalerci, Thilo Michael, Robin Schaefer +1
cs.CLarXiv:2608.17827v12026
Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention Recommenders
Keito Kozaki, Keigo Sakurai, Ren Togo +2
cs.AIcs.IRarXiv:2608.14021v12026
Repair, Not Improvement: Decomposing Constrained Decoding in Tool-Call Abstention
Janghoon Lee
cs.CLarXiv:2608.13959v12026
What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
Chen Huang, Yuhao Wu, Wenxuan Zhang
cs.AIarXiv:2606.05304v12026
Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning
Chun-Hua Lin, Samuel Yen-Chi Chen, Yu-Chao Hsu +7
cs.LGcs.AIcs.DCarXiv:2608.13914v12026
Forget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speech
Hyoeun Kim, Yujun Lee, Kyuhong Shim
cs.SDcs.AIarXiv:2609.27399v12026
TuneJury: An Open Metric for Improving Music Generation Preference Alignment
Yonghyun Kim, Junwon Lee, Haiwen Xia +5
cs.SDcs.AIcs.LGarXiv:2606.17006v12026
SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior
Mingyue Cui, Linghui Shen, Xingyi Yang
cs.LGcs.AIarXiv:2606.18322v12026
Quantifying the Gap Between Laboratory Battery Test Patterns and Field Duty Profiles
Chunyang Zhao, Chresten Træholt
cs.LGarXiv:2608.16212v12026
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
Bobo Li, Hao Fei, Tianjie Ju +2
cs.AIcs.CLarXiv:2608.13558v12026
Summaries:한국어
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models
Sen Xu, Shixi Liu, Wei Wang +6
cs.AIcs.CLarXiv:2606.16140v12026

Every paper with a summary

Redakto - The Incognito Tab for LLMs

Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning

Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda

Pre-training Visual Dexterity in Simulation

Safety Alignment Illusion: The Cross-Lingual Safety Gap in LLMs

GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation

PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection

TokenPowerSandbox: Evidence-Gated CPU-First Screening for Energy-Aware LLM Serving

Investigating Forecast Proficiency of Hurricane-Induced Compound Flooding With a Discontinuous Galerkin Shallow Water Equation Solver

Entity tracking emerges in sub-billion parameter language models and exceeds human performance in naturalistic narratives

OOD Detection for EEG-based Machine Learning in High-Risk Environments

FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model

Beyond What Meets the Eye: Unveiling Situational Illusions for Multimodal Large Language Models

Sparse Token Routing in Efficient Transformers

From Entity Mentions to Tone: An LLM-Based Pipeline for Media Bias Analysis

TRACE-BN: Transferring Bangla-English Tutoring Behavior to a Sub-1B Offline Language Model

TRACE: Artifact-Robust Statistical Shape Modeling from Imperfect Surface Scans - A Case Study in Craniosynostosis 3D Photography

What Does CLIP Learn for Regional Geolocalization? Probing Visual Cues and Scene Configuration After Adaptation

A Pilot Study of Autocompleting Tokenizers

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

ARGUS: Theory-of-Mind Guided Argument Generation with Strategy-Aware Planning and Knowledge Grounding

CRS-Bench: A Reference-Relative Reliability Benchmark for Medical Image Encoders

Poly-InstructTTS: Learning In-the-Wild Expressive Speech Synthesis from Open-Ended Instructions

ViPO: Visual Preference Optimization at Scale

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

The Divergence Hypothesis: Unmasking Lexical Interference and Label Bias in Mental Health NLP

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

TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection

AISA: AI Safety Assistant Framework for Continuous Improvement of Highway Construction

Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation

Prediction of Prediction (PoP): Inter-Layer Activation Fusion for Single-Pass Hallucination Detection in Large Language Models

A Comprehensive Survey of Wireless Foundation Models for AI-Native 6G Networks

A Few Cases Are All You Need: An Empirical Study of Annotation-Efficient LoRA Fine-Tuning of MedSAM3

FedPref: Federated Preference Learning for Structured Radiology Report Extraction

Software Frameworks for Explainable AI in Time Series Classification: A Systematic Review

A-CPES: A Reference Framework for Agentic AI in Cyber-Physical Energy Systems

Effective Personalized AI Tutors via LLM-Guided Reinforcement Learning

Do Not Copy/Paste: Soft Barriers for Copying in AI-Assisted Programming

When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents

FrenchNews-7: Benchmarking Cross-Publisher French News Editorial Desk Classification

Beyond Two Bytes per Letter: Tokenization Overhead in Cyrillic AI Systems

Reviewing Model Collapse and Countermeasures

How Much Do Legal RAG Systems Still Hallucinate?

H$^2$SD: Hybrid Hindsight Self-Distillation

Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge

Decoupling Planning and Control for Instructable Agents

Data-Driven Reconstruction of Spatially Resolved Electron and Ion Energy Distributions from Macroscopic Plasma Quantities with Deep Neural Networks

When Adaptation Hurts: Connecting Representational Drift to OOD Failures in MedSAM Fine-Tuning

Benchmarking Patent Drafting from Inventor-Style Disclosures

From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sector

Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention Recommenders

Repair, Not Improvement: Decomposing Constrained Decoding in Tool-Call Abstention

What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems

Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning

Forget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speech

TuneJury: An Open Metric for Improving Music Generation Preference Alignment

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

Quantifying the Gap Between Laboratory Battery Test Patterns and Field Duty Profiles

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models