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)

24,181 to 24,240 of 27,217

Auditory Illusion Benchmark for Large Audio Language Models
Hayoon Kim, Eunice Hong, Kyogu Lee
cs.SDcs.AIarXiv:2609.02277v12026
World Models for Embodied Intelligence: From Plausible to Controllable to Actionable
Nanjie Yao, Hao Wang, Chong Cheng +10
cs.ROcs.AIarXiv:2609.16697v12026
Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation
Teresa DiMeola, Charles Walter, Hong Xiao
cs.CVcs.AIarXiv:2609.00628v12026
In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning
Iliano Fasolino
cs.CRcs.AIcs.CLarXiv:2609.09243v12026
Can AI Agents Detect and Repair Artifact Drift in Network Experiments?
Tianzhu Zhang, Weichen Tao, Changgang Zheng +4
cs.NIcs.AIeess.SYarXiv:2609.09849v12026
Physics-Informed Foresight Pruning for Sparse PINN Solvers of Nonlinear PDEs
Ahmad Ishaque Karimi, Uvini Balasuriya Mudiyanselage, Kookjin Lee
cs.LGcs.AIarXiv:2608.25564v12026
When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning
Yitong Guo, Xiaoyi Chen, Siyuan Zhang +2
cs.CRcs.AIarXiv:2609.01455v12026
HALDETECT at ImageEval 2026 Shared Tasks: Answer-First Contrastive Grounding with QLoRA
Syed Mohaiminul Hoque, Md Sakhawat Hossain
cs.CVcs.AIarXiv:2609.11236v12026
Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise
Mika Okamoto, Gabriele Sarti
cs.AIcs.CLarXiv:2609.07139v12026
AV-SafetyBench: A Safety Benchmark for Text-to-Audio-Video Generation
Suah Choi, Tae-Young Lee, Gyeong-Moon Park
cs.CVcs.AIarXiv:2609.06991v12026
Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech
Chibuzor Okocha, Christan Earl Grant
cs.CLcs.AIarXiv:2609.11786v12026
Comparative Study of Anatomical and Learned Features in AI Models for Structural Brain MRI
Boyang Yu, Miquel Lopez Escoriza, Long Chen +3
cs.CVcs.AIarXiv:2609.06807v12026
Combining Self-Embedding Audio Watermarking with Ultra-Low-Bitrate Neural Codecs
Yigitcan Özer, Xin Wang, Zhe Zhang +1
cs.SDcs.AIarXiv:2608.25289v12026
LCoT-GV: Graph Attention Networks for Verifying Long Reasoning Chains in Large Language Models
Bérénice Jaulmes, Mehwish Alam
cs.CLcs.AIarXiv:2608.30679v12026
MCP-Driven Accessibility Tree Standardization for AI-Powered Screen Reader Agents
Vishnu Ramineni, Nitin Saksena, Akash Kumar Agarwal +5
cs.HCcs.AIarXiv:2608.24898v12026
Automating Quadratic Unconstrained Binary Optimization (QUBO) Formulation Generation from Natural Language
Niloy Kumar Mondal, Md Rizwan Parvez
cs.AIarXiv:2609.10629v12026
PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?
Mika Okamoto, Ansel Kaplan Erol
cs.CLcs.AIcs.CYarXiv:2609.18605v12026
Watermarks Without Verification: AI Text Watermarking After the EU AI Act
Alexander Nemecek, Vipin Chaudhary, Erman Ayday
cs.CYcs.AIcs.CRarXiv:2609.09604v12026
Learning from What You Retrieve: Online RL Fine-Tuning for Semantic Retrieval
Shaowei Wei, Chong Huang, Songtao Fang +3
cs.IRcs.AIarXiv:2608.30753v12026
Fine-Grained Multi Image Object Hallucination Benchmark
Joonki Min, Chaeyun Kim, Hyungwook Choi +4
cs.CVcs.AIcs.LGarXiv:2608.30653v12026
Neurosymbolics for Data Engineering: Achieving Long Context Token Reduction Without Finetuning
Vishvesh Bhat
cs.CLcs.AIcs.LGarXiv:2609.00367v12026
Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized Checkpoints
Junlong Shen Xingyu Li
cs.AIcs.LGarXiv:2609.11490v12026
A Unified Physics-Aware Quantum Machine Learning Framework across Power GaN HEMTs and Logic Nanowire FETs: Predicting Unseen Process Splits and Held-Out Geometry Combinations with Lower Error and Tighter Split-to-Split Variability
Rushat Rai, Yun-Yuan Wang, Autsada Kakaen +10
cs.AIarXiv:2609.05251v12026
What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection
Zhinan Hou, Jiaqi Zhang, Xunliang Cai +1
cs.AIarXiv:2609.05198v12026
Review Before Trust: Source-Grounded Integrity Gates for AI-Assisted Personal Health Records
Nora Girda, Adrian Groza
cs.AIarXiv:2608.29965v12026
Predicting Radiologist Expertise from 3D Gaze Patterns During CT Interpretation
Leila Khaertdinova, Anna Anikina, Claudia Mello-Thoms +1
cs.CVcs.AIcs.LGarXiv:2608.23836v12026
Towards Stream Learning on Embedded Systems: Benchmarking the Memory Consumption of Stream Learning Methods
Sebastian Buschjäger, Nuwan Gunasekara, Heitor Murilo Gomes
cs.LGcs.AIcs.PFarXiv:2608.30923v12026
Dynamic Heterogeneous Graph Representation Learning: A Survey
Huan Liu, Pengfei Jiao, Jie Yin +2
cs.LGcs.AIcs.SIarXiv:2609.04779v12026
The Natural Language Interaction Protocol and Standard for AI Agents
Luyi Xing, Rasit Onur Topaloglu, Ranjan Sinha +9
cs.AIarXiv:2609.04135v12026
Conducting Stylistic Analysis of Paintings through an Art-History Agent
Marc S. Walton, Astrid Harth
cs.CVcs.AIcs.CLarXiv:2608.29644v12026
It's All in the Way You Say It: The Role of Information Representation in LLM-Based Glycemic-Event Prediction
Andrea Apicella, Pasquale Arpaia, Matteo Orefice +2
cs.AIarXiv:2609.08772v12026
An AI-Powered Culturally Aware Chatbot for Stress Detection and Wellness Support among Pakistani University Students Using NLP and Machine Learning
Muhammad Fahad Bashir, Muhammad Afzal
cs.AIarXiv:2609.11199v12026
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
Junyao Yang, Yucheng Shi, Zhongzhi Li +4
cs.LGcs.AIarXiv:2609.11042v12026
VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification
Yixin Wan, Tianle Zheng, Kai-Wei Chang
cs.CVcs.AIcs.CLarXiv:2609.06245v12026
The reach of a verification tool decides its value: A controlled study of verification surface, artifact quality, and cost in AI coding agents
Achint Mehta
cs.SEcs.AIarXiv:2608.28795v12026
ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs
Yizhan Li, Jianxin You, Mengyang Xiong +5
cs.ROcs.AIarXiv:2609.10895v12026
Inducing Emergent Misalignment from Reward Hacks with Iterative DPO
Oliver Daniels, Perusha Moodley, Benjamin M. Marlin +1
cs.LGcs.AIarXiv:2609.06649v12026
What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation
Ziyue Wang, Aomufei Yuan, Yiran Yao +10
cs.CLcs.AIarXiv:2608.22948v12026
Albedo Estimation via Latent Bridge Matching
Carme Corbi, David Serrano-Lozano, Javier Vazquez-Corral +1
cs.CVcs.AIarXiv:2609.09884v12026
Development of an Autonomous AI Coding Agent using Monte Carlo Tree Search (MCTS) and Gemini LLM Frameworks
Pravin Game, Vipin Ramakrishnan, Prathamesh Wagh
cs.LGcs.AIarXiv:2608.29096v12026
Do General NLP Embeddings Capture Ontological Reasoning?
Hamed Babaei Giglou, Jennifer D'Souza, Sören Auer
cs.CLcs.AIarXiv:2609.00177v12026
LLM-Guided Program Evolution for Circle Packing: Breaking 10 Packomania Records for $28
Wes Sander
cs.AIarXiv:2609.05093v12026
An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks
Viet K. Nguyen, Mohammad I. Husain
cs.CRcs.AIarXiv:2609.09404v12026
Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning
Yaning Jia, Chunhui Zhang, Wenxuan Xu +3
cs.AIarXiv:2609.09707v12026
From State Synchronization to Cognitive Self-Evolution: An Operational Architecture for Cognitive Digital Twins
Haoran Gao, An Li, Zhen Li +1
cs.AIarXiv:2609.09625v12026
ProtLingo: Efficient Protein Language Modeling via Conditional Memory and Expert Routing
Mingrui Li, Sixian Shen, Minzhang Li +4
cs.AIarXiv:2609.04793v12026
SCCM : Stream Cruise Control Method for Automated Drift Detection and Adaptation
Mohammad Abu-Shaira, Weishi Shi
cs.LGcs.AIarXiv:2609.09432v12026
A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation
Rahul Khedar, Eshita, Sneha Teja Sree Reddy Thondapu +6
cs.AIcs.CLarXiv:2609.08592v12026
Text Restoration of Ancient Documents with Language Models
Shibingfeng Zhang, Edoardo Caraffa, Annafelicia Zuffrano +2
cs.CLcs.AIarXiv:2608.28170v12026
FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality
Abhishek Sharma
cs.AIarXiv:2609.04706v12026
When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models
Gnaneswar Villuri, Hashmath Shaik, Alex Doboli
cs.CLcs.AIarXiv:2609.04582v12026
PACE: Publisher-Adaptive Content Extraction via Agentic Automation
Zhanlin Liu, Munirathnam Srikanth
cs.CLcs.AIarXiv:2608.27466v12026
Understanding Deep Learning via Entropy Space Theory
Li Li, Tong Zhang, Wentao Yu +1
cs.AIarXiv:2608.29279v12026
CALIPER: Clean Scenes Cannot Rank Physical Inference in Pretrained Visual Representations
Aman Mehta, Riya Baviskar
cs.ROcs.AIcs.CVarXiv:2609.08250v12026
Rethinking World Models for Safety-Critical Embodied Systems
Kailang Ma, Heye Huang, Inhi Kim +1
cs.AIcs.ROarXiv:2609.03774v12026
Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents
Jalal Mahmud
cs.AIcs.IRarXiv:2609.02129v12026
Complexity Induction: Compositional Generalization via Structured Label Distortion
Aleksandr Abramov
cs.CVcs.AIcs.LGarXiv:2608.21464v12026
Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection
Xuechao Zou, Yi Zhou, Kai Li +4
cs.CVcs.AIarXiv:2609.07670v12026
The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing
Chenguang Wang, Ming Li, Adebayo Braimah +6
cs.AIcs.CLarXiv:2609.07713v12026
There Is No Neutral Harness: Modern LLM Leaderboards Are Manufactured by Config-Fragile Items
V. S. Raghu Parupudi
cs.AIarXiv:2608.21382v12026

Artificial Intelligence

Auditory Illusion Benchmark for Large Audio Language Models

World Models for Embodied Intelligence: From Plausible to Controllable to Actionable

Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation

In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning

Can AI Agents Detect and Repair Artifact Drift in Network Experiments?

Physics-Informed Foresight Pruning for Sparse PINN Solvers of Nonlinear PDEs

When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning

HALDETECT at ImageEval 2026 Shared Tasks: Answer-First Contrastive Grounding with QLoRA

Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise

AV-SafetyBench: A Safety Benchmark for Text-to-Audio-Video Generation

Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech

Comparative Study of Anatomical and Learned Features in AI Models for Structural Brain MRI

Combining Self-Embedding Audio Watermarking with Ultra-Low-Bitrate Neural Codecs

LCoT-GV: Graph Attention Networks for Verifying Long Reasoning Chains in Large Language Models

MCP-Driven Accessibility Tree Standardization for AI-Powered Screen Reader Agents

Automating Quadratic Unconstrained Binary Optimization (QUBO) Formulation Generation from Natural Language

PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?

Watermarks Without Verification: AI Text Watermarking After the EU AI Act

Learning from What You Retrieve: Online RL Fine-Tuning for Semantic Retrieval

Fine-Grained Multi Image Object Hallucination Benchmark

Neurosymbolics for Data Engineering: Achieving Long Context Token Reduction Without Finetuning

Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized Checkpoints

A Unified Physics-Aware Quantum Machine Learning Framework across Power GaN HEMTs and Logic Nanowire FETs: Predicting Unseen Process Splits and Held-Out Geometry Combinations with Lower Error and Tighter Split-to-Split Variability

What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection

Review Before Trust: Source-Grounded Integrity Gates for AI-Assisted Personal Health Records

Predicting Radiologist Expertise from 3D Gaze Patterns During CT Interpretation

Towards Stream Learning on Embedded Systems: Benchmarking the Memory Consumption of Stream Learning Methods

Dynamic Heterogeneous Graph Representation Learning: A Survey

The Natural Language Interaction Protocol and Standard for AI Agents

Conducting Stylistic Analysis of Paintings through an Art-History Agent

It's All in the Way You Say It: The Role of Information Representation in LLM-Based Glycemic-Event Prediction

An AI-Powered Culturally Aware Chatbot for Stress Detection and Wellness Support among Pakistani University Students Using NLP and Machine Learning

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification

The reach of a verification tool decides its value: A controlled study of verification surface, artifact quality, and cost in AI coding agents

ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs

Inducing Emergent Misalignment from Reward Hacks with Iterative DPO

What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation

Albedo Estimation via Latent Bridge Matching

Development of an Autonomous AI Coding Agent using Monte Carlo Tree Search (MCTS) and Gemini LLM Frameworks

Do General NLP Embeddings Capture Ontological Reasoning?

LLM-Guided Program Evolution for Circle Packing: Breaking 10 Packomania Records for $28

An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks

Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning

From State Synchronization to Cognitive Self-Evolution: An Operational Architecture for Cognitive Digital Twins

ProtLingo: Efficient Protein Language Modeling via Conditional Memory and Expert Routing

SCCM : Stream Cruise Control Method for Automated Drift Detection and Adaptation

A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation

Text Restoration of Ancient Documents with Language Models

FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality

When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models

PACE: Publisher-Adaptive Content Extraction via Agentic Automation

Understanding Deep Learning via Entropy Space Theory

CALIPER: Clean Scenes Cannot Rank Physical Inference in Pretrained Visual Representations

Rethinking World Models for Safety-Critical Embodied Systems

Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents

Complexity Induction: Compositional Generalization via Structured Label Distortion

Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection

The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing

There Is No Neutral Harness: Modern LLM Leaderboards Are Manufactured by Config-Fragile Items