Artificial Intelligence

Papers filed under cs.AI on arXiv, each one already summarized by Paperlayer. 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)

12,961 to 13,020 of 15,414

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
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
Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference
Christos Koutsiaris
cs.IRcs.AIcs.CLarXiv:2608.20210v12026
Accurate and scalable exchange-correlation with deep learning
Giulia Luise, Chin-Wei Huang, Thijs Vogels +25
physics.chem-phcs.AIcs.CEarXiv:2506.14665v62025
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
CreativeGame:Toward Mechanic-Aware Creative Game Generation
Hongnan Ma, Han Wang, Shenglin Wang +6
cs.AIarXiv:2604.19926v12026
Tadabur: A Large-Scale Quran Audio Dataset
Faisal Alherran
cs.SDcs.AIarXiv:2604.18932v12026
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
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
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
ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation
Zhiqin Yang, Zhenyuan Zhang, Xianzhang Jia +4
cs.AIarXiv:2604.19211v12026
ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning
Xianming Li, Zongxi Li, Tsz-fung Andrew Lee +3
cs.CLcs.AIarXiv:2604.19254v12026
MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings
Zijie Li, Yichun Shi, Jingxiang Sun +8
cs.CVcs.AIcs.LGarXiv:2604.19902v12026
SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution
Xiachong Feng, Yi Jiang, Xiaocheng Feng +9
cs.AIarXiv:2604.18982v12026
Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts
Chaitanya Dwivedi, Binxuan Huang, Himanshu Gupta +3
cs.LGcs.AIarXiv:2604.19835v22026
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
Venus Team, Sunhao Dai, Yong Deng +10
cs.LGcs.AIcs.CLarXiv:2604.19859v12026
UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
Boyu Chen, Yi Chen, Lu Qiu +3
cs.ROcs.AIarXiv:2604.19734v12026
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
Noah Flynn
cs.LGcs.AIcs.CLarXiv:2604.20720v12026
Image Generators are Generalist Vision Learners
Valentin Gabeur, Shangbang Long, Songyou Peng +22
cs.CVcs.AIarXiv:2604.20329v32026
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
Xiyang Wu, Zongxia Li, Guangyao Shi +5
cs.AIarXiv:2604.20987v12026
Seeing Fast and Slow: Learning the Flow of Time in Videos
Yen-Siang Wu, Rundong Luo, Jingsen Zhu +6
cs.CVcs.AIcs.GRarXiv:2604.21931v12026
TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale
Jun Wang, Ziyin Zhang, Rui Wang +3
cs.CLcs.AIcs.LGarXiv:2604.21889v32026
Learning Evidence Highlighting for Frozen LLMs
Shaoang Li, Yanhang Shi, Yufei Li +10
cs.CLcs.AIarXiv:2604.22565v22026
OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism
Xiangyu Li, Huaizhi Tang, Xin Ding +3
cs.ROcs.AIarXiv:2603.14371v22026
Hybrid Policy Distillation for LLMs
Wenhong Zhu, Ruobing Xie, Rui Wang +1
cs.CLcs.AIarXiv:2604.20244v22026
Building a Precise Video Language with Human-AI Oversight
Zhiqiu Lin, Chancharik Mitra, Siyuan Cen +13
cs.CVcs.AIcs.CLarXiv:2604.21718v22026
Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models
Vipula Rawte, Ryan Rossi, Franck Dernoncourt +1
cs.AIarXiv:2604.21193v12026
Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
Tharindu Kumarage, Lisa Bauer, Yao Ma +7
cs.AIarXiv:2604.22119v22026
AgentSearchBench: A Benchmark for AI Agent Search in the Wild
Bin Wu, Arastun Mammadli, Xiaoyu Zhang +1
cs.AIcs.IRcs.MAarXiv:2604.22436v12026
SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation
Harshit Joshi, Priyank Shethia, Jadelynn Dao +1
cs.CLcs.AIarXiv:2604.22294v22026
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Meng Chu, Xuan Billy Zhang, Kevin Qinghong Lin +47
cs.AIarXiv:2604.22748v32026
Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization
Jiarui Yao, Ruida Wang, Hao Bai +1
cs.LGcs.AIcs.CLarXiv:2601.10201v22026
XSkill: Continual Learning from Experience and Skills in Multimodal Agents
Guanyu Jiang, Zhaochen Su, Xiaoye Qu +1
cs.AIcs.CLarXiv:2603.12056v32026
Primal Acceleration of Newton's Method
Nikita Doikov
math.OCcs.AIcs.LGarXiv:2608.21359v12026
AI with Authority, from Application to Silicon
Jason Hickey
cs.SEcs.AIcs.ARarXiv:2608.21356v12026
TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems
Vladimir Bataev, Lilit Grigoryan, Andrei Andrusenko +3
eess.AScs.AIcs.CLarXiv:2608.21343v12026
Target-Aware Calibration Data Selection for Preserving Uncertainty in Quantized Language Models
Zhen Yang, Sizai Hou, Kaiwen Zheng +4
cs.CLcs.AIarXiv:2608.21019v12026
EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering
Xuanyu Meng, Jiashuo Sun, Jash Rajesh Parekh +1
cs.CLcs.AIcs.DBarXiv:2608.21252v12026
Utility Under Attack: Agent Memory Poisoning and the Limits of Content Screening and Provenance Ranking
Arulnidhi Karunanidhi
cs.CRcs.AIarXiv:2608.21230v12026
SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control
Ruihua Han, Rui Gao, Zhe Liu +6
cs.ROcs.AIarXiv:2608.21175v12026
CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agents
Jiancheng Wang, Mingli Zhu, Tong Zhang +4
cs.CVcs.AIarXiv:2608.21114v12026
AID-Guard: Stateful Authorization for Delegated Agent Effects
Yingzhe Tong, Leyu Dai, Songhui Guo
cs.CRcs.AIarXiv:2608.21159v12026
HIERA: Workload-Aware Planning Across Implementation Spaces for GPU Kernel Optimization
Jinghao Wang, Qiqi Gu, Chenpeng Wu +3
cs.DCcs.AIarXiv:2608.21157v12026
PromptResponse: Optimizing Prompts for LLM Coding Tasks
Erik Thureck, Robert Kühnen, Tim Jacobowitz
cs.CLcs.AIcs.HCarXiv:2608.21074v12026
A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans
Simon Vincent Abel, Heiko Hillenhagen, Michael Götz +3
cs.CVcs.AIarXiv:2608.21140v12026
Free-Text Evaluation of LLMs for 5G Domain Knowledge and Fault Analysis using LLM-as-Judge
Rishiraj Sengupta, Sotiris Chatzimiltis, Mohammad Shojafar +1
cs.CLcs.AIcs.NIarXiv:2608.21021v12026
Jacobian-guided Noise Injection for Quantization Robustness in Large Language Models
Deepanshu Pandey, Arnav Chavan, Nahush Lele +2
cs.LGcs.AIarXiv:2608.20988v12026
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs
Bakbergen Ryskulov, Iker García-Ferrero, David Montero +5
cs.CLcs.AIcs.LGarXiv:2608.20953v12026
Extractive Summarization for Arabic Documents Using SAraBERT with a Semantic Siamese Similarity Evaluation Metric
Sami Shames El Deen, Mariette Awad
cs.CLcs.AIarXiv:2608.20964v12026
Vibe Coding and Web Application Security: A Twin-Prompt Study
Darko Andročec
cs.CRcs.AIarXiv:2608.20963v12026
BC-Bench: Evaluating Agentic Engineering in a Domain-Specific Language for ERP
Haoran Sun, Klaus Marius Hansen
cs.SEcs.AIarXiv:2608.20851v12026
Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting
Lan Guo, Jie Xiao, Zhao Su +5
cs.LGcs.AIarXiv:2608.20761v12026
TRACE: Training-time Report-guided and Clinically Ordered Concept Editing
Wentao Yue, Tianyou Lai, Jiayu Luo +4
cs.CVcs.AIarXiv:2608.20809v12026
PSK at WMT 2026 MIST: Task-Specialized QLoRA Adapters for Multilingual Summarization and Question Answering
Srikar Kashyap Pulipaka
cs.CLcs.AIcs.LGarXiv:2608.20757v12026
Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning
Haonan Jia, Shichao Dong, Zenghui Sun +7
cs.CVcs.AIarXiv:2608.21305v12026
Temporal Validity on Real Software Histories: Eliminating Stale-Fact Errors in Code-Assistant Memory over GitHub Fixes
Neeraj Yadav
cs.SEcs.AIcs.CLarXiv:2608.20685v12026
Adapting Knowledge Graphs for Behavior Denoising in Sequential Recommendation
Zichun Jin, Zihan Zhou, Yinan Liu +2
cs.IRcs.AIarXiv:2608.21243v12026

Artificial Intelligence

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

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

LLM Safety From Within: Detecting Harmful Content with Internal Representations

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

Accurate and scalable exchange-correlation with deep learning

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

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

CreativeGame:Toward Mechanic-Aware Creative Game Generation

Tadabur: A Large-Scale Quran Audio Dataset

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

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

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

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

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

ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning

MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings

SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution

Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts

DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data

UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling

COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling

Image Generators are Generalist Vision Learners

Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks

Seeing Fast and Slow: Learning the Flow of Time in Videos

TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale

Learning Evidence Highlighting for Frozen LLMs

OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism

Hybrid Policy Distillation for LLMs

Building a Precise Video Language with Human-AI Oversight

Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models

Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework

AgentSearchBench: A Benchmark for AI Agent Search in the Wild

SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization

XSkill: Continual Learning from Experience and Skills in Multimodal Agents

Primal Acceleration of Newton's Method

AI with Authority, from Application to Silicon

TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems

Target-Aware Calibration Data Selection for Preserving Uncertainty in Quantized Language Models

EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering

Utility Under Attack: Agent Memory Poisoning and the Limits of Content Screening and Provenance Ranking

SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control

CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agents

AID-Guard: Stateful Authorization for Delegated Agent Effects

HIERA: Workload-Aware Planning Across Implementation Spaces for GPU Kernel Optimization

PromptResponse: Optimizing Prompts for LLM Coding Tasks

A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans

Free-Text Evaluation of LLMs for 5G Domain Knowledge and Fault Analysis using LLM-as-Judge

Jacobian-guided Noise Injection for Quantization Robustness in Large Language Models

Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs

Extractive Summarization for Arabic Documents Using SAraBERT with a Semantic Siamese Similarity Evaluation Metric

Vibe Coding and Web Application Security: A Twin-Prompt Study

BC-Bench: Evaluating Agentic Engineering in a Domain-Specific Language for ERP

Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting

TRACE: Training-time Report-guided and Clinically Ordered Concept Editing

PSK at WMT 2026 MIST: Task-Specialized QLoRA Adapters for Multilingual Summarization and Question Answering

Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning

Temporal Validity on Real Software Histories: Eliminating Stale-Fact Errors in Code-Assistant Memory over GitHub Fixes

Adapting Knowledge Graphs for Behavior Denoising in Sequential Recommendation