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)

3,601 to 3,660 of 15,344

EC-SAGINs: Edge Computing-enhanced Space-Air-Ground Integrated Networks for Internet of Vehicles
Shuai Yu, Xiaowen Gong, Qian Shi +2
cs.NIcs.AIcs.DCarXiv:2101.06056v12021
Deriving Neural Scaling Laws from the statistics of natural language
Francesco Cagnetta, Allan Raventós, Surya Ganguli +1
cs.LGcs.AIstat.MLarXiv:2602.07488v32026
The information geometry of product-reference discrete diffusion: Interaction growth complexity and optimal scheduling
Martin J. Wainwright
stat.MLcs.AIcs.LGarXiv:2608.28949v12026
Preconditioning Benefits of Spectral Orthogonalization in Muon
Jianhao Ma, Yu Huang, Yuejie Chi +1
cs.LGcs.AImath.OCarXiv:2601.13474v12026
ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
Hongjue Zhao, Haosen Sun, Jiangtao Kong +8
cs.AIarXiv:2602.17560v22026
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
Ruiyan Han, Zhen Fang, XinYu Sun +9
cs.CVcs.AIarXiv:2601.03193v22026
Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs
Alessio Borgi, Mario Severino, Fabrizio Silvestri +1
cs.LGcs.AIarXiv:2608.28853v12026
S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds
Ran Cheng, Christopher Agia, Yuan Ren +2
cs.CVcs.AIcs.LGarXiv:2012.09242v12020
How Powerful are K-hop Message Passing Graph Neural Networks
Jiarui Feng, Yixin Chen, Fuhai Li +2
cs.LGcs.AIarXiv:2205.13328v42022
FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems
Shanli Xing, Yiyan Zhai, Alexander Jiang +10
cs.AIarXiv:2601.00227v12026
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
Hongyang Du, Junjie Ye, Xiaoyan Cong +7
cs.CVcs.AIcs.LGarXiv:2601.23286v42026
ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation
Yitong Han, Wei Gao, Yi Zhao +3
cs.CLcs.AIcs.LGarXiv:2609.00057v12026
Towards Efficient and Scalable Sharpness-Aware Minimization
Yong Liu, Siqi Mai, Xiangning Chen +2
cs.LGcs.AIcs.CVarXiv:2203.02714v12022
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
Chang Jin, An Wang, Zeming Wei +7
cs.CRcs.AIcs.CLarXiv:2605.12015v32026
Inkspire: Supporting Design Exploration with Generative AI through Analogical Sketching
David Chuan-En Lin, Hyeonsu B. Kang, Nikolas Martelaro +3
cs.HCcs.AIcs.CVarXiv:2501.18588v12025
MemRec: Collaborative Memory-Augmented Agentic Recommender System
Weixin Chen, Yuhan Zhao, Jingyuan Huang +6
cs.IRcs.AIarXiv:2601.08816v32026
Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy
Yi-Cheng Lai, Hen-Hsen Huang
cs.CLcs.AIarXiv:2609.00067v12026
A Deep Framework for Cross-Domain and Cross-System Recommendations
Feng Zhu, Yan Wang, Chaochao Chen +3
cs.LGcs.AIarXiv:2009.06215v12020
Medical Causal Hypothesis Verification with Large Language Models
Safiyyah Ahmed, Abrar Ansari, Md Aminul Islam +1
cs.CLcs.AIarXiv:2609.00063v12026
Distilling Policy Distillation
Wojciech Marian Czarnecki, Razvan Pascanu, Simon Osindero +3
cs.LGcs.AIstat.MLarXiv:1902.02186v12019
Can LLM Agents Discover? Evaluating Creativity on ML Engineering Tasks
Shitanshu Bhushan, Yunxiang Zhang, Lu Wang
cs.AIarXiv:2608.30047v12026
How do LLMs Compute Verbal Confidence
Dharshan Kumaran, Arthur Conmy, Federico Barbero +3
cs.CLcs.AIcs.LGarXiv:2603.17839v32026
Structurally Aligned Subtask-Level Memory for Software Engineering Agents
Kangning Shen, Jingyuan Zhang, Chenxi Sun +2
cs.SEcs.AIarXiv:2602.21611v12026
A Survey on Interpretable Reinforcement Learning
Claire Glanois, Paul Weng, Matthieu Zimmer +4
cs.LGcs.AIarXiv:2112.13112v22021
Gradient Flow Drifting: Generative Modeling via Wasserstein Gradient Flows of KDE-Approximated Divergences
Jiarui Cao, Zixuan Wei, Yuxin Liu
cs.LGcs.AIarXiv:2603.10592v12026
TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
Kai Li, Xuanqing Yu, Ziyi Ni +9
cs.CLcs.AIarXiv:2601.02845v22026
INTERVenE: Temporal-Abstraction-Interval Based Transformers for Short-Horizon Medical Event Prediction
Shahar Oded, Yuval Shahar
cs.LGcs.AIarXiv:2608.29901v12026
Active Context Compression: Autonomous Memory Management in LLM Agents
Nikhil Verma
cs.AIarXiv:2601.07190v12026
Graph-based Agent Memory: Taxonomy, Techniques, and Applications
Chang Yang, Chuang Zhou, Yilin Xiao +15
cs.AIarXiv:2602.05665v12026
Real Money, Fake Models: Deceptive Model Claims in Shadow APIs
Yage Zhang, Yukun Jiang, Zeyuan Chen +3
cs.CRcs.AIcs.SEarXiv:2603.01919v22026
SWE-bench Goes Live!
Linghao Zhang, Shilin He, Chaoyun Zhang +12
cs.SEcs.AIcs.CLarXiv:2505.23419v22025
PALR: Personalization Aware LLMs for Recommendation
Fan Yang, Zheng Chen, Ziyan Jiang +3
cs.IRcs.AIcs.CLarXiv:2305.07622v32023
Exploring Silicon-Based Societies: An Early Study of the Moltbook Agent Community
Yu-Zheng Lin, Bono Po-Jen Shih, Hsuan-Ying Alessandra Chien +6
cs.MAcs.AIcs.CYarXiv:2602.02613v42026
Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing
Yelysei Bondarenko, Markus Nagel, Tijmen Blankevoort
cs.LGcs.AIcs.CLarXiv:2306.12929v22023
Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction
Darius A. Faroughy, Sofia Palacios Schweitzer, Ian Pang +2
cs.LGcs.AIhep-exarXiv:2605.13950v12026
Large-scale online deanonymization with LLMs
Simon Lermen, Daniel Paleka, Joshua Swanson +3
cs.CRcs.AIcs.LGarXiv:2602.16800v22026
StructMem: Structured Memory for Long-Horizon Behavior in LLMs
Buqiang Xu, Yijun Chen, Jizhan Fang +5
cs.CLcs.AIcs.IRarXiv:2604.21748v12026
Enhancing SAE-based Steering via Neighbor Integrated Feature Selection
Yutian Liu, Xu Wang, Difan Zou
cs.AIarXiv:2608.28806v12026
Compound Deception in Elite Peer Review: A Failure Mode Taxonomy of 100 Fabricated Citations at NeurIPS 2025
Samar Ansari
cs.DLcs.AIarXiv:2602.05930v12026
DexterityGen: Foundation Controller for Unprecedented Dexterity
Zhao-Heng Yin, Changhao Wang, Luis Pineda +11
cs.ROcs.AIcs.LGarXiv:2502.04307v12025
MathScale: Scaling Instruction Tuning for Mathematical Reasoning
Zhengyang Tang, Xingxing Zhang, Benyou Wang +1
cs.CLcs.AIcs.LGarXiv:2403.02884v12024
One-Class Adversarial Nets for Fraud Detection
Panpan Zheng, Shuhan Yuan, Xintao Wu +2
cs.LGcs.AIcs.CRarXiv:1803.01798v22018
MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering
Fangyu Liu, Francesco Piccinno, Syrine Krichene +6
cs.CLcs.AIcs.CVarXiv:2212.09662v22022
When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications
Qidong Liu, Xian Wu, Xiangyu Zhao +4
cs.CLcs.AIarXiv:2310.18339v22023
One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
Adheesh Sunil Juvekar, Onkar Kishor Susladkar, Kiet A. Nguyen +6
cs.CVcs.AIarXiv:2609.04190v12026
This human study did not involve human subjects: Validating LLM simulations as behavioral evidence
Jessica Hullman, David Broska, Huaman Sun +1
cs.AIarXiv:2602.15785v12026
On the Plasticity Collapse in Continual Machine Unlearning
Yingdan Shi, Xiang Xu, Kaize Ding +2
cs.LGcs.AIarXiv:2608.29513v12026
Consistent feature attribution for tree ensembles
Scott M. Lundberg, Su-In Lee
cs.AIcs.LGstat.MLarXiv:1706.06060v62017
Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells
Gengchen Mai, Krzysztof Janowicz, Bo Yan +3
cs.CVcs.AIcs.LGarXiv:2003.00824v12020
Balance of Benchmarks: Semantic Density Reweighting for Benchmark Multiplicity and Task-Conditioned Evaluation
Jhen-Ke Lin
cs.AIcs.CLcs.LGarXiv:2608.30044v12026
BetterV: Controlled Verilog Generation with Discriminative Guidance
Zehua Pei, Hui-Ling Zhen, Mingxuan Yuan +2
cs.AIcs.PLarXiv:2402.03375v32024
Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
Soroush Vosoughi, Prashanth Vijayaraghavan, Deb Roy
cs.CLcs.AIcs.NEarXiv:1607.07514v12016
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
Mubashara Akhtar, Anka Reuel, Prajna Soni +34
cs.AIarXiv:2602.16763v42026
Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning
Cameron Voloshin, Hoang M. Le, Nan Jiang +1
cs.LGcs.AIcs.ROarXiv:1911.06854v32019
Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization
Xiang Fang, Wanlong Fang, Changshuo Wang
cs.CVcs.AIarXiv:2605.26501v12026
LingoQA: Visual Question Answering for Autonomous Driving
Ana-Maria Marcu, Long Chen, Jan Hünermann +9
cs.ROcs.AIcs.CVarXiv:2312.14115v42023
Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management
Yiming Zhang, Kun Yang, Cong Shen +1
eess.SYcs.AIarXiv:2608.28878v12026
Adaptive Memory Admission Control for LLM Agents
Guilin Zhang, Wei Jiang, Xiejiashan Wang +5
cs.AIcs.CLcs.MAarXiv:2603.04549v12026
AgentTrace: A Structured Logging Framework for Agent System Observability
Adam AlSayyad, Kelvin Yuxiang Huang, Richik Pal
cs.SEcs.AIarXiv:2602.10133v12026
RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction
Tianyi Wang, Jiazhou Chen, Yiming Xu +7
cs.ROcs.AIcs.CVarXiv:2608.28718v12026

Artificial Intelligence

EC-SAGINs: Edge Computing-enhanced Space-Air-Ground Integrated Networks for Internet of Vehicles

Deriving Neural Scaling Laws from the statistics of natural language

The information geometry of product-reference discrete diffusion: Interaction growth complexity and optimal scheduling

Preconditioning Benefits of Spectral Orthogonalization in Muon

ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs

S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds

How Powerful are K-hop Message Passing Graph Neural Networks

FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems

VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation

ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation

Towards Efficient and Scalable Sharpness-Aware Minimization

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

Inkspire: Supporting Design Exploration with Generative AI through Analogical Sketching

MemRec: Collaborative Memory-Augmented Agentic Recommender System

Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy

A Deep Framework for Cross-Domain and Cross-System Recommendations

Medical Causal Hypothesis Verification with Large Language Models

Distilling Policy Distillation

Can LLM Agents Discover? Evaluating Creativity on ML Engineering Tasks

How do LLMs Compute Verbal Confidence

Structurally Aligned Subtask-Level Memory for Software Engineering Agents

A Survey on Interpretable Reinforcement Learning

Gradient Flow Drifting: Generative Modeling via Wasserstein Gradient Flows of KDE-Approximated Divergences

TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents

INTERVenE: Temporal-Abstraction-Interval Based Transformers for Short-Horizon Medical Event Prediction

Active Context Compression: Autonomous Memory Management in LLM Agents

Graph-based Agent Memory: Taxonomy, Techniques, and Applications

Real Money, Fake Models: Deceptive Model Claims in Shadow APIs

SWE-bench Goes Live!

PALR: Personalization Aware LLMs for Recommendation

Exploring Silicon-Based Societies: An Early Study of the Moltbook Agent Community

Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing

Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction

Large-scale online deanonymization with LLMs

StructMem: Structured Memory for Long-Horizon Behavior in LLMs

Enhancing SAE-based Steering via Neighbor Integrated Feature Selection

Compound Deception in Elite Peer Review: A Failure Mode Taxonomy of 100 Fabricated Citations at NeurIPS 2025

DexterityGen: Foundation Controller for Unprecedented Dexterity

MathScale: Scaling Instruction Tuning for Mathematical Reasoning

One-Class Adversarial Nets for Fraud Detection

MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering

When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications

One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing

This human study did not involve human subjects: Validating LLM simulations as behavioral evidence

On the Plasticity Collapse in Continual Machine Unlearning

Consistent feature attribution for tree ensembles

Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells

Balance of Benchmarks: Semantic Density Reweighting for Benchmark Multiplicity and Task-Conditioned Evaluation

BetterV: Controlled Verilog Generation with Discriminative Guidance

Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder

When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning

Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization

LingoQA: Visual Question Answering for Autonomous Driving

Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management

Adaptive Memory Admission Control for LLM Agents

AgentTrace: A Structured Logging Framework for Agent System Observability

RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction