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)

13,921 to 13,980 of 15,210

A Survey of Large Language Models
Wayne Xin Zhao, Kun Zhou, Junyi Li +19
cs.CLcs.AIarXiv:2303.18223v192023
Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions
Ruiyang Qin, Qingzhuo Wang, Tian Wang +2
cs.LGcs.AIcs.CLarXiv:2608.18539v12026
MorphoGP: A Nonparametric Framework for Predicting Equilibrium Beach Profiles Under Tidal Influence
Xi Wu, Yanqing Wei, Hang Yin +3
cs.LGcs.AIphysics.geo-pharXiv:2608.18558v12026
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai +3
cs.CLcs.AIcs.LGarXiv:2106.07447v12021
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Peng Wang, Shuai Bai, Sinan Tan +16
cs.CVcs.AIcs.CLarXiv:2409.12191v22024
GPT-4o System Card
OpenAI, :, Aaron Hurst +417
cs.CLcs.AIcs.CVarXiv:2410.21276v12024
CentaurBench: Benchmarking LLM Capabilities on Augmenting vs. Automating Real-World Work Tasks
Pattaraphon Kenny Wongchamcharoen, Kris Gulati, Min Min Fong +1
cs.CYcs.AIcs.MAarXiv:2608.18554v12026
DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents
Hangrui Xu, Jiarui Wang, Yang Yang +5
cs.CLcs.AIcs.LGarXiv:2608.18524v12026
Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscripts
Kartik Chincholikar, Kaushik Gopalan, Mihir Hasabnis
cs.CVcs.AIarXiv:2608.18696v12026
Composed Historical Image Retrieval by Modeling Temporal Representations
Adrià Molina Rodríguez, Oriol Ramos Terrades, Josep Lladós Canet
cs.CVcs.AIcs.IRarXiv:2608.18694v12026
Europe's Climate Ambition Under Scrutiny: Evidence from Deep Learning Emission Projections
Jacopo Ghirri, Carlos Rodriguez-Pardo, Lara Aleluia Reis +1
cs.LGcs.AIecon.GNarXiv:2608.18690v12026
OmniHandwritingOCR: A Diagnostic Benchmark for Evaluating Multimodal LLMs in Handwritten OCR Scenarios
Zinuo Guo, Min Zhang, Bo Jiang
cs.CVcs.AIarXiv:2608.18586v12026
Reflexion: Language Agents with Verbal Reinforcement Learning
Noah Shinn, Federico Cassano, Edward Berman +3
cs.AIcs.CLcs.LGarXiv:2303.11366v42023
Variational Inference with Normalizing Flows
Danilo Jimenez Rezende, Shakir Mohamed
stat.MLcs.AIcs.LGarXiv:1505.05770v62015
OptiModNet: A UNet-Transformer Hybrid with Grouped-Query and Channel Attention for Optic Disc and Cup Segmentation
Soumili Ghosh, Debapriya Roy, Aryan Das +1
cs.CVcs.AIarXiv:2608.18516v12026
Coverage-Driven RTL Assertion Generation with Formal Exploration and Neuro-Symbolic Refinement
Zhiyuan Yan, Ziyue Zheng, Hongce Zhang
cs.ARcs.AIarXiv:2608.18482v12026
SeisEvo: Evolution of Seismic Data Reconstruction Algorithms by Agents
Yingjie Xu, Siwei Yu, Jianwei Ma
physics.geo-phcs.AIcs.NEarXiv:2608.18272v12026
FedCoRe: Target-Adaptive Completion for Missing Modalities in Healthcare Federated Learning
Holger R. Roth, Ziyue Xu, Peter Cnudde
cs.CVcs.AIcs.LGarXiv:2608.18311v12026
TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs
Muhammad Haseeb Aslam, Alessandro Koerich, Marco Pedersoli +2
cs.CVcs.AIarXiv:2608.18386v12026
A Survey Of Methods For Explaining Black Box Models
Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri +3
cs.CYcs.AIcs.LGarXiv:1802.01933v32018
One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI
Gaston Besanson
cs.SEcs.AIcs.CYarXiv:2608.18360v12026
EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents
Weixian Xu, Shilong Liu, Mengdi Wang
cs.LGcs.AIarXiv:2606.11182v12026
Science Done on a Machine by a Machine: AI Agents in Computational Chemistry
Pavlo O. Dral, Hassan Nawaz, Arif Ullah
physics.chem-phcs.AIphysics.comp-pharXiv:2608.18508v12026
Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents
Alexander Tu, Michael Tu
cs.CRcs.AIcs.LGarXiv:2608.18351v12026
ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics
Shunkai Zhang, Haoran Zhang, Yun Luo +15
cs.AIarXiv:2606.10479v12026
ERASE: EaRly bAckpropagation SchEdule for Faster Training of Modern Recommendation Systems
Ergan Shang, Flavio Sales Truzzi
cs.LGcs.AIarXiv:2608.18469v12026
Pedagogical AI in Mental Health: A Tri-Stream Fine-Tuned LLM Framework for Automated Clinical Supervision and Risk Triage
Shreeya Sharma, Ravish Gupta, Saket Kumar +1
cs.CLcs.AIcs.LGarXiv:2608.18438v12026
Summaries:한국어 日本語简体中文 Español Français Deutsch
Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B
Rahul Chowdhury, Timothy A Rupprecht, Senhao Cao +5
cs.LGcs.AIarXiv:2608.18419v12026
Vector Symbolic Policy Gradient
Ryozo Masukawa, Sanggeon Yun, SungHeon Jeong +6
cs.LGcs.AIcs.SCarXiv:2608.18404v12026
LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents
Daehong Kim, Haichao Miao, Shusen Liu
cs.HCcs.AIarXiv:2608.18398v12026
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models
Cheng-Yu Yang, Shao-Yuan Lo, Yu-Lun Liu
cs.CVcs.AIarXiv:2606.12412v12026
One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA
Zhi Zheng, Ziqiao Meng, Hao Luan +2
cs.AIarXiv:2606.10572v12026
Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation
Guiv Farmanfarmaian
cs.LGcs.AIcs.CLarXiv:2608.18379v12026
Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring
Steven C. Nesbit, Victor M. Vergara, Michael A. Felix +4
cs.NEcs.AIcs.ETarXiv:2608.18341v12026
Coupled-cluster molecular properties across the main group that extrapolate beyond training size
Wenhao He, Xu Chen, Noah Song +10
physics.chem-phcond-mat.mtrl-scics.AIarXiv:2608.18346v12026
SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
Dustin Podell, Zion English, Kyle Lacey +5
cs.CVcs.AIarXiv:2307.01952v12023
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
Peter Clark, Isaac Cowhey, Oren Etzioni +4
cs.AIcs.CLcs.IRarXiv:1803.05457v12018
Visual-Prompt Guided Wildlife Instance-Level Recognition
Mufhumudzi Muthivhi, Jiahao Huo, Terence van Zyl +1
cs.CVcs.AIcs.LGarXiv:2608.18246v12026
Accurate Decoding of Natural Sentences from Non-Invasive Brain Recordings
Mingfang Zhang, Jarod Lévy, Cedric Rommel +9
cs.CLcs.AIcs.LGarXiv:2608.18114v12026
TokenPowerSandbox: Evidence-Gated CPU-First Screening for Energy-Aware LLM Serving
Chenxu Niu
cs.ARcs.AIcs.DCarXiv:2608.18149v12026
LAION-5B: An open large-scale dataset for training next generation image-text models
Christoph Schuhmann, Romain Beaumont, Richard Vencu +13
cs.CVcs.AIcs.LGarXiv:2210.08402v12022
Improved Baselines with Visual Instruction Tuning
Haotian Liu, Chunyuan Li, Yuheng Li +1
cs.CVcs.AIcs.CLarXiv:2310.03744v22023
Bidirectional representational alignment between biological and artificial neural networks
Samuel Kostousov, Abhinn Kaushik, Brokoslaw Laschowski
cs.LGcs.AIarXiv:2608.18244v12026
GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction
Ziyang Cheng, Tianshu Tang, Jinxin Lan +17
cs.ROcs.AIcs.LGarXiv:2608.18234v12026
Bound-Aware Per-Organ Recall Risk Control for Multi-Organ CT Segmentation under Clinical Domain Shift
Souraj Adhikary, Negar Chabi, Andre Mastmeyer
cs.CVcs.AIcs.LGarXiv:2608.18193v12026
Towards A Rigorous Science of Interpretable Machine Learning
Finale Doshi-Velez, Been Kim
stat.MLcs.AIcs.LGarXiv:1702.08608v22017
Language Models for Portuguese: A Systematic Mapping Study
Jhessica Silva, Carlos Caetano, Helena Maia +3
cs.CLcs.AIarXiv:2608.18138v12026
Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
Haixu Wu, Jiehui Xu, Jianmin Wang +1
cs.LGcs.AIarXiv:2106.13008v52021
What Can Artificial Intelligence Learn from Medicine? Generative Analogies and Reliable Machine Learning Systems
Emanuele Ratti, Lena Zuchowski
cs.LGcs.AIcs.CYarXiv:2608.18186v12026
Are LLMs Safe Beyond Text: Do Emojis Expose Gaps in Safety Evaluation
M P V S Gopinadh
cs.CLcs.AIcs.CRarXiv:2608.18164v12026
When Do LLMs Actually Help? Evaluating LLMs as Data Quality Annotators
Praphulla Lal Shrestha
cs.CLcs.AIarXiv:2608.18158v12026
The Deontic Gap: Large Language Models and the Modal Language of Obligation
Daniel Hart, Sarah Allred, Joseph Abbas +1
cs.CLcs.AIarXiv:2608.18144v12026
Explanation in Artificial Intelligence: Insights from the Social Sciences
Tim Miller
cs.AIarXiv:1706.07269v32017
Same Facts, Different Updates: Inference Setup Shapes LLM Behavior in Medical Allocation
Spencer Gibson, Tyler Crosse, Magnus Saebo +3
cs.CLcs.AIcs.HCarXiv:2608.18108v12026
OpenAI Gym
Greg Brockman, Vicki Cheung, Ludwig Pettersson +4
cs.LGcs.AIarXiv:1606.01540v12016
Different Facets of Verbalised Overconfidence: an Interpretability Study
Davide Mazzaccara, Leonardo Bertolazzi, Raffaella Bernardi
cs.CLcs.AIarXiv:2608.18106v12026
Flow Matching for Generative Modeling
Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu +2
cs.LGcs.AIstat.MLarXiv:2210.02747v22022
Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery
Alizer Wong, Heng Cui, Yi Tan +6
cs.AImath.NTarXiv:2608.19047v12026
Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
Valentin Romanov, Monique Bax, Steven Niederer
cs.AIcs.DBarXiv:2608.19025v12026
A Theory of Post-hoc Debate Judgement
Xiang Yin, Adam Dejl, Antonio Rago +2
cs.AIarXiv:2608.19002v12026

Artificial Intelligence

A Survey of Large Language Models

Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions

MorphoGP: A Nonparametric Framework for Predicting Equilibrium Beach Profiles Under Tidal Influence

HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

GPT-4o System Card

CentaurBench: Benchmarking LLM Capabilities on Augmenting vs. Automating Real-World Work Tasks

DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents

Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscripts

Composed Historical Image Retrieval by Modeling Temporal Representations

Europe's Climate Ambition Under Scrutiny: Evidence from Deep Learning Emission Projections

OmniHandwritingOCR: A Diagnostic Benchmark for Evaluating Multimodal LLMs in Handwritten OCR Scenarios

Reflexion: Language Agents with Verbal Reinforcement Learning

Variational Inference with Normalizing Flows

OptiModNet: A UNet-Transformer Hybrid with Grouped-Query and Channel Attention for Optic Disc and Cup Segmentation

Coverage-Driven RTL Assertion Generation with Formal Exploration and Neuro-Symbolic Refinement

SeisEvo: Evolution of Seismic Data Reconstruction Algorithms by Agents

FedCoRe: Target-Adaptive Completion for Missing Modalities in Healthcare Federated Learning

TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs

A Survey Of Methods For Explaining Black Box Models

One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI

EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents

Science Done on a Machine by a Machine: AI Agents in Computational Chemistry

Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents

ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics

ERASE: EaRly bAckpropagation SchEdule for Faster Training of Modern Recommendation Systems

Pedagogical AI in Mental Health: A Tri-Stream Fine-Tuned LLM Framework for Automated Clinical Supervision and Risk Triage

Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B

Vector Symbolic Policy Gradient

LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation

Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring

Coupled-cluster molecular properties across the main group that extrapolate beyond training size

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Visual-Prompt Guided Wildlife Instance-Level Recognition

Accurate Decoding of Natural Sentences from Non-Invasive Brain Recordings

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

LAION-5B: An open large-scale dataset for training next generation image-text models

Improved Baselines with Visual Instruction Tuning

Bidirectional representational alignment between biological and artificial neural networks

GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction

Bound-Aware Per-Organ Recall Risk Control for Multi-Organ CT Segmentation under Clinical Domain Shift

Towards A Rigorous Science of Interpretable Machine Learning

Language Models for Portuguese: A Systematic Mapping Study

Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting

What Can Artificial Intelligence Learn from Medicine? Generative Analogies and Reliable Machine Learning Systems

Are LLMs Safe Beyond Text: Do Emojis Expose Gaps in Safety Evaluation

When Do LLMs Actually Help? Evaluating LLMs as Data Quality Annotators

The Deontic Gap: Large Language Models and the Modal Language of Obligation

Explanation in Artificial Intelligence: Insights from the Social Sciences

Same Facts, Different Updates: Inference Setup Shapes LLM Behavior in Medical Allocation

OpenAI Gym

Different Facets of Verbalised Overconfidence: an Interpretability Study

Flow Matching for Generative Modeling

Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery

Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models

A Theory of Post-hoc Debate Judgement