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)

10,501 to 10,560 of 15,398

Toxicity in ChatGPT: Analyzing Persona-assigned Language Models
Ameet Deshpande, Vishvak Murahari, Tanmay Rajpurohit +2
cs.CLcs.AIcs.LGarXiv:2304.05335v12023
Language Models can Solve Computer Tasks
Geunwoo Kim, Pierre Baldi, Stephen McAleer
cs.CLcs.AIcs.HCarXiv:2303.17491v32023
AI and the Everything in the Whole Wide World Benchmark
Inioluwa Deborah Raji, Emily M. Bender, Amandalynne Paullada +2
cs.LGcs.AIcs.PFarXiv:2111.15366v12021
DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision
Lu Ling, Yichen Sheng, Zhi Tu +17
cs.CVcs.AIarXiv:2312.16256v22023
Goodput Maximization for Large Language Model Edge Inference: A Two-Phase Maskable PPO Approach
Xiaojing Chen, Qi Zhang, Wei Ni +2
eess.SYcs.AIarXiv:2608.25543v12026
Revelation Control
Qinyou Wang
cs.LGcs.AIstat.MLarXiv:2608.23860v12026
Summaries:한국어
FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference
Gongwei Lee, Ji Liu, Juncheng Jia +1
cs.LGcs.AIcs.DCarXiv:2608.24945v12026
Summaries:한국어
Spending Scarce Confirmatory PET Measurements: Target-Aligned Validation in A4/LEARN
Eliuvish Han Cui
stat.APcs.AIcs.LGarXiv:2608.22223v12026
Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep
Pedro Santos
cs.MAcs.AIcs.SEarXiv:2608.23395v12026
Names Can Hurt: Spotting Slopsquatting Risks Caused by Package Name Hallucinations in Local Coding LLMs
Akash Raj, Sargam Sahu
cs.CLcs.AIarXiv:2608.23897v12026
CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search
Xiaolong Sun, Qichao Wang, Hangyu Li +1
cs.AIcs.CVarXiv:2608.25023v12026
CacheRouter: A Dual-Path Tool Routing Architecture with Cache-Preserving Main-Model Isolation for Long-Tail Tool Discovery
Donghui Zha, Lingwei Xu, Linxiao Wu +2
cs.AIarXiv:2608.22708v12026
Correcting a learned physical invariant improves world-model rollouts
Richard Bao
cs.AIarXiv:2608.23526v12026
Why Does Robustness Reduce Superposition?
Adam Elimadi
cs.LGcs.AIarXiv:2608.22155v12026
STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Control
Mengxi Luo, Changjia Chen, An Cao +2
cs.AIarXiv:2608.22538v12026
ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration
Juntong Wu, Yifei Liu, Junyi Chen +6
cs.LGcs.AIarXiv:2608.24938v12026
When Does Frequency Decomposition Benefit Physics-Informed Neural Networks? A Preliminary Ablation Study
Shubham Rai
cs.LGcs.AIarXiv:2608.24940v12026
A Mathematical Theory of Interpretation: Rational Entropy, Spectral Readout, and Confusability as a Resource
Blake Reynolds
cs.ITcs.AIarXiv:2608.23892v12026
Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring
Olga Manakina, Igor Bogdanov
cs.LGcs.AIcs.CLarXiv:2608.23814v12026
Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders
Igor Bogdanov, Changcheng Huang
cs.LGcs.AIcs.CLarXiv:2608.23809v12026
What Reaches Expert Review? Representation, Structural Screening, and Candidate-Form Dependence in AI-Assisted Item Development
Christopher Brooks
cs.CLcs.AIarXiv:2608.23766v12026
Beyond Executable Models: The Pufibara Agent Harness and the Modelica Agent Workflow Benchmark for Physical System Modeling
Zizhe Wang
cs.SEcs.AIarXiv:2608.23653v12026
Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watched Fail
Esmail Gumaan
cs.SEcs.AIarXiv:2608.23651v12026
Retrieval-augmented generation vs. deterministic tax computation in multi-agent financial advisory: A 2x2 factorial experiment
Aryan Brar, Justin Du, Avery Lor +2
cs.AIarXiv:2608.23908v12026
Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors
Joshua Penman
cs.AIcs.CLcs.CRarXiv:2608.23873v12026
SyPS: Measuring Sycophancy Prompt Sensitivity in Large Language Models
Lijia Huang, Yao Fu, Sihao Ren
cs.AIarXiv:2608.23837v12026
When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World
Xiang Chen, Zeyu Zhang
cs.CLcs.AIarXiv:2608.23507v12026
Adversarial Entropy Inflation Against Gumbel-Based Inference Verification
Nikita Kezins
cs.CRcs.AIarXiv:2608.23375v12026
Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval
Kishore Konda
cs.IRcs.AIarXiv:2608.22980v12026
Targeting the Attention Heads Behind Object Hallucination in LLaVA
Armaan Sandhu, Abhilasha Senapati, Hima Kammachi
cs.CVcs.AIarXiv:2608.24966v12026
Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching
Jiarui Cao
cs.LGcs.AIarXiv:2608.25138v12026
Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation
Peng Liu, Huibing Zeng, Yiqun Zhang +2
cs.LGcs.AIcs.ETarXiv:2608.24973v12026
The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models
Augusto Camargo
cs.AIcs.CLcs.CYarXiv:2608.24662v22026
Unmatched Does Not Mean False: Incomplete Reference Sets Can Reverse Calibration Rankings in Open-Ended Theory-of-Mind Tracking
Zhexi Feng, Wuxi Chen, Bingrui Zhang
cs.CLcs.AIarXiv:2608.25654v12026
Output Dilution: Redundant but Fragile Representations in MoE Models
Orion Reblitz-Richardson
cs.LGcs.AIcs.CLarXiv:2608.25231v12026
Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows
Miao Liu, Zhizhe Liu
cs.CLcs.AIarXiv:2608.24842v12026
Knowing When to Ask for Help: Bayesian Self-Escalation in Hierarchical LLM Agents
Nadeem Shaikh
cs.LGcs.AIstat.MLarXiv:2608.24087v12026
Constrained Entity Selection under Partial Knowledge for LLM-Based Knowledge Graph QA
Emanuel Kitzelmann
cs.AIarXiv:2608.24824v12026
Confident at the moment of action: belief miscalibration in LLM play under hidden information
Bhushan Kashinath Joshi
cs.AIcs.CLcs.LGarXiv:2608.24691v12026
Do Recipes Have Personas? Characterizing and Generating Creator Style in Attributed Procedural Graphs
Lei Jiang
cs.AIarXiv:2608.24369v12026
Benchmarking LLM Judges for Voice-Agent Evaluation: Reliability, Calibration, and Human Oversight
Anupam Purwar, Shashank Singh, Kritika Srivastava
cs.AIcs.ETarXiv:2608.24314v12026
VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models
Guoyang Xu, Hao Chen
cs.AIarXiv:2608.24302v12026
Giraffe: A Mapping Architecture from Hidden Text Representations to Visual Embeddings for Efficient Graphic Design
Nejla Ghaboosi
cs.AIcs.LGarXiv:2608.23970v12026
MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities
Tianshi Wang, Jingsong Wang, Yafei Huang +3
cs.CRcs.AIcs.MMarXiv:2608.25490v12026
RotDroid: Cross-Orientation State Equivalence Testing for Detecting GUI Rotation Bugs in Android Apps
Mengdi Qin, Bo Jiang
cs.SEcs.AIarXiv:2608.25425v12026
A Tendon-Driven Five-Fingered Hand with Distributed Tactile Perception for Dexterous Manipulation
Huayang Chen, Longhui Qin
cs.ROcs.AIarXiv:2608.25547v12026
PIVOT: A Multi-Trajectory Dataset and Testbed for Pose, Intrinsics, and Novel Viewpoint Evaluation in Real-World 3D Reconstruction
Mary Raymond
cs.CVcs.AIarXiv:2608.25401v12026
Neither Precision Nor Architecture Alone: Controlled Tests of Failure Remedies for Physics-Informed Neural Networks
Jinyuan Zhang, Peng He, He Hu +2
cs.LGcs.AIarXiv:2608.25327v12026
PonsRAG: A Pons-Inspired RAG Bridging Cognitive Islands for Coordinated Long Narrative Reasoning
Rongchen Zhao, Yu Chen, Juyuan Wang +4
cs.AIcs.CLarXiv:2608.25486v12026
Escaping Low-Dimensional Overlap: Multi-Task Model Merging via High-Dimensional Sparse Disentanglement
Yihang Zhang, Shengke Sun, Junjie Wen +1
cs.LGcs.AIcs.CLarXiv:2608.25354v12026
When Less Is More: An Empirical Study of Minimal Responses in Counseling Dialogues and the Behavior of LLMs
Zhiyang Qi
cs.CLcs.AIarXiv:2608.24080v12026
Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems
Zhongwen Luan, Xiaoyu Zhang, Ming Hu +3
cs.AIcs.SEarXiv:2608.25920v12026
Summaries:简体中文
A Statistical Audit of Physical AI Benchmark Redundancy
Zaruhi Navasardyan, Hrant Davtyan
cs.ROcs.AIarXiv:2608.25940v12026
A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training
Kaichen Li, Zhilin Zhu, Jianhao Huang +7
cs.CVcs.AIarXiv:2608.26095v12026
TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding
Yuqiang Lin, Yan Shi, Sam Lockyer +5
cs.CVcs.AIarXiv:2608.25935v12026
From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis
Haiyu Huang, Jiewei Lyu, Zhihan Jiang +5
cs.SEcs.AIarXiv:2608.25661v12026
Summaries:简体中文
Choose Your Game Wisely: Measuring Game-Theoretic Structures in Real-World Vehicle Interactions
Yueyuan Li, Rongcheng Nie, Weijie Xi +4
cs.AIcs.ROarXiv:2608.25917v12026
Gating Before Commitment: Anticipating Intent Divergence to Prevent Post-Interaction Decision Failures in Autonomous Driving
Cong Xu, Ravi Sankar
cs.ROcs.AIarXiv:2608.26074v12026
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
Alexander Robey, Eric Wong, Hamed Hassani +1
cs.LGcs.AIstat.MLarXiv:2310.03684v42023
FRAME: separating sampling variation from representational cause in medical imaging fairness
Mahshad Lotfinia, Daniel Truhn, Andreas Maier +1
cs.CVcs.AIcs.LGarXiv:2608.25981v12026

Artificial Intelligence

Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Language Models can Solve Computer Tasks

AI and the Everything in the Whole Wide World Benchmark

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision

Goodput Maximization for Large Language Model Edge Inference: A Two-Phase Maskable PPO Approach

Revelation Control

FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference

Spending Scarce Confirmatory PET Measurements: Target-Aligned Validation in A4/LEARN

Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep

Names Can Hurt: Spotting Slopsquatting Risks Caused by Package Name Hallucinations in Local Coding LLMs

CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search

CacheRouter: A Dual-Path Tool Routing Architecture with Cache-Preserving Main-Model Isolation for Long-Tail Tool Discovery

Correcting a learned physical invariant improves world-model rollouts

Why Does Robustness Reduce Superposition?

STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Control

ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration

When Does Frequency Decomposition Benefit Physics-Informed Neural Networks? A Preliminary Ablation Study

A Mathematical Theory of Interpretation: Rational Entropy, Spectral Readout, and Confusability as a Resource

Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring

Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders

What Reaches Expert Review? Representation, Structural Screening, and Candidate-Form Dependence in AI-Assisted Item Development

Beyond Executable Models: The Pufibara Agent Harness and the Modelica Agent Workflow Benchmark for Physical System Modeling

Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watched Fail

Retrieval-augmented generation vs. deterministic tax computation in multi-agent financial advisory: A 2x2 factorial experiment

Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors

SyPS: Measuring Sycophancy Prompt Sensitivity in Large Language Models

When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World

Adversarial Entropy Inflation Against Gumbel-Based Inference Verification

Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval

Targeting the Attention Heads Behind Object Hallucination in LLaVA

Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching

Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation

The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models

Unmatched Does Not Mean False: Incomplete Reference Sets Can Reverse Calibration Rankings in Open-Ended Theory-of-Mind Tracking

Output Dilution: Redundant but Fragile Representations in MoE Models

Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows

Knowing When to Ask for Help: Bayesian Self-Escalation in Hierarchical LLM Agents

Constrained Entity Selection under Partial Knowledge for LLM-Based Knowledge Graph QA

Confident at the moment of action: belief miscalibration in LLM play under hidden information

Do Recipes Have Personas? Characterizing and Generating Creator Style in Attributed Procedural Graphs

Benchmarking LLM Judges for Voice-Agent Evaluation: Reliability, Calibration, and Human Oversight

VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models

Giraffe: A Mapping Architecture from Hidden Text Representations to Visual Embeddings for Efficient Graphic Design

MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities

RotDroid: Cross-Orientation State Equivalence Testing for Detecting GUI Rotation Bugs in Android Apps

A Tendon-Driven Five-Fingered Hand with Distributed Tactile Perception for Dexterous Manipulation

PIVOT: A Multi-Trajectory Dataset and Testbed for Pose, Intrinsics, and Novel Viewpoint Evaluation in Real-World 3D Reconstruction

Neither Precision Nor Architecture Alone: Controlled Tests of Failure Remedies for Physics-Informed Neural Networks

PonsRAG: A Pons-Inspired RAG Bridging Cognitive Islands for Coordinated Long Narrative Reasoning

Escaping Low-Dimensional Overlap: Multi-Task Model Merging via High-Dimensional Sparse Disentanglement

When Less Is More: An Empirical Study of Minimal Responses in Counseling Dialogues and the Behavior of LLMs

Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems

A Statistical Audit of Physical AI Benchmark Redundancy

A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training

TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding

From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis

Choose Your Game Wisely: Measuring Game-Theoretic Structures in Real-World Vehicle Interactions

Gating Before Commitment: Anticipating Intent Divergence to Prevent Post-Interaction Decision Failures in Autonomous Driving

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

FRAME: separating sampling variation from representational cause in medical imaging fairness