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)

14,281 to 14,340 of 15,403

MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
Han Chen, Zining Zhang, Wenqi Pei +6
cs.DBcs.AIcs.MAarXiv:2605.23986v22026
Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State
Fanzhe Wei, Li Liu
cs.AIarXiv:2608.15810v12026
PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation
Zhiyuan Yuan, Guanying Chen, Lingteng Qiu +3
cs.CVcs.AIcs.GRarXiv:2608.16984v12026
Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
Mohammadreza Armandpour, Fatih Ilhan, David Harrison +6
cs.LGcs.AIarXiv:2605.10889v12026
Towards One-to-Many Temporal Grounding
Qi Xu, Yue Tan, Shihao Chen +5
cs.CVcs.AIarXiv:2606.06294v22026
Rethinking Irregular Time Series Forecasting from the Perspective of Basis Functions
Rongwen Li, Changjian Chen
cs.LGcs.AIarXiv:2608.17284v12026
HarmProfile: Characterizing Harmful Distributions in Frontier LLMs
Zhouyuan Ma, Yutao Wu, Hanxun Huang +6
cs.CLcs.AIarXiv:2608.14577v12026
Lance: Unified Multimodal Modeling by Multi-Task Synergy
Fengyi Fu, Mengqi Huang, Shaojin Wu +10
cs.CVcs.AIarXiv:2605.18678v22026
Beyond Single Object: Learning 3D Relations with Large Language Models
Kohsuke Ide, Ryousuke Yamada, Yue Qiu +4
cs.CVcs.AIcs.CLarXiv:2608.15710v12026
Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields
Liya Zhu, Jingzhe Ding, Jian Zhang +63
cs.AIarXiv:2606.11042v42026
Augmenting Text to Increase Translation Difficulty
William Kalikman, Šimon Sukup, Michal Tešnar +1
cs.AIarXiv:2608.15932v12026
More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts
Víctor Yeste, Paolo Rosso
cs.CLcs.AIcs.LGarXiv:2605.22641v32026
TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration
Hanzhi Zhang, Qiao Zhang, Qinglei Cao +4
cs.AIarXiv:2608.17336v12026
Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning
Yanxi Chen, Weijie Shi, Yuexiang Xie +4
cs.LGcs.AIcs.CLarXiv:2606.20002v12026
ARASH: Adaptive Retrieval And Shot Selection for Tabular Prediction
Samirasadat Jamalidinan, Yue Xu, Kazem Cheshmi
cs.AIarXiv:2608.17856v12026
SkillEffect: Checked Lowering for Memory-Bounded Agent Tools
Yinuo Wang, Yiyu Shi
cs.AIarXiv:2608.17007v12026
Authorization Before Context: A Model-Neutral Audience Boundary Against Cross-Audience Memory Leakage in Agentic Systems
Sibo Liu
cs.CRcs.AIarXiv:2608.17148v12026
Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline
Mikhail Surikov
cs.CRcs.AIcs.SEarXiv:2608.16187v12026
GRIP: Grounded Reasoning via Information-Restricted Premises
Lirui Teng
cs.AIarXiv:2608.16776v12026
Graph Surgery and the Do-Operator: A Precise Correspondence for Acyclic Structural Causal Models
Satpreet Makhija
cs.AIcs.PLarXiv:2608.17634v12026
AutoResearch: Insight In, Hallucination Out
Yiming Ren, Xiang Liu, Qumeng Sun +4
cs.AIcs.MAarXiv:2608.17906v12026
SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoning
Guozheng Sun
cs.AIarXiv:2608.17301v12026
The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence
Neeraj Kumar Singh Beshane
cs.CRcs.AIarXiv:2608.17176v12026
Behaviour Is an Incomplete Measure of Reasoning Development: Cross-surface pre-arrival accessibility and the limits of developmental inference in a recurrent-depth reasoner
Simon Lam-Muir
cs.LGcs.AIarXiv:2608.16085v12026
Auditing Self-Evolution in Financial Agents: Capability Gains, Security Drift, and Execution-Interface Mismatch
Jialong Li, Jialing Zhu
cs.AIarXiv:2608.17684v12026
Historical Backtesting for Scientific Question Discovery: A Protocol and Astronomy Pilot
Hui Mao
cs.CEcs.AIarXiv:2608.16795v12026
Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text
Benjamin Belay
cs.CLcs.AIarXiv:2608.16868v12026
Bounded Semantic Planning and Deterministic Compilation for Reliable Enterprise Text-to-SQL
Yi Ai
cs.DBcs.AIarXiv:2608.16663v12026
Training with synthetic data for drone detection in thermal imagery
Tanel Liiv, Sander Soodla, Nzamba Bignoumba +2
cs.CVcs.AIcs.ETarXiv:2608.17799v12026
Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps
Zirui Song, Yuye Zhu, Yang Yang
cs.IRcs.AIarXiv:2608.16309v12026
Decoupled Temporal Encoding for Generative Recommendation
Pengfei Jia, Jingjian Wang, Jingmao Li +2
cs.IRcs.AIarXiv:2608.16274v12026
DeepInsight II: One Trace from Benchmark to Robot
Siyi Li, Yuchen Kang, Wuliang Wang +4
cs.AIarXiv:2608.16556v12026
Quipu: A Governed Bitemporal Knowledge Graph Store
Steve Brown
cs.AIcs.DBarXiv:2608.16813v12026
Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection
Bin Li, Dongdong Wang, Siyang Lu
cs.LGcs.AIcs.SEarXiv:2608.17965v12026
Grading Needs a Rubric, Not Intelligence
Jhen-Ke Lin
cs.CLcs.AIarXiv:2608.17938v12026
Beyond MSE: Rethinking the Evaluation Metric and Benchmarking for Irregular Time Series Forecasting
Rongwen Li, Haixin Xie, Xiao Wang +1
cs.LGcs.AIarXiv:2608.17293v12026
What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations
Xiaonan Xu, Wenjing Wu
cs.SEcs.AIcs.CLarXiv:2608.17719v12026
Delta2Gamma: Band-Wise Adaptive Contrastive Learning of EEG for Alzheimer's Disease Detection
Chanwoo Park, Chanwoo Kim
cs.LGcs.AIarXiv:2608.17231v12026
D$^2$ACCI: A Dual-Loop Diagnostic Protocol for Evidence-Preserving Agent Memory
Xule Liu, Yijun Liu, Chao Li +1
cs.AIarXiv:2608.17756v12026
Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing
Kang Chen, Sihan Zhao, Yixin Cao +1
cs.AIarXiv:2608.17638v12026
Average Distance Approximation for Static Large Graphs
Kartikey Ahlawat
cs.DScs.AIcs.CGarXiv:2608.16916v12026
CoAL-RAG: A Complexity-Aware Legal Retrieval-Augmented Generation Method
Jin Su, Zhuofeng Zhao, Huanhuan Wang +1
cs.CLcs.AIarXiv:2608.17536v12026
The Price of Anarchy in Disaggregated Inference
Athos Georgiou
cs.ARcs.AIcs.DCarXiv:2606.17081v12026
FastMix: Fast Data Mixture Optimization via Gradient Descent
Haoru Tan, Sitong Wu, Yanfeng Chen +5
cs.LGcs.AIarXiv:2606.14971v12026
EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video
Hyunjin Kim, Ri-Zhao Qiu, Guangqi Jiang +1
cs.CVcs.AIcs.ROarXiv:2606.16202v12026
AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties
Yifan Jiang, Meige Yang, Zitong Li +1
cs.AIarXiv:2606.14240v12026
Rethinking RAG in Long Videos: What to Retrieve and How to Use It?
Yuho Lee, Jisu Shin, Nicole Hee-Yeon Kim +5
cs.AIarXiv:2606.13141v12026
A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets
Tejas Agrawal, Vu Le, Sumit Gulwani +1
cs.SEcs.AIcs.HCarXiv:2606.13802v12026
HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing
Haoran You, Yotam Nitzan, Lingzhi Zhang +7
cs.CVcs.AIarXiv:2606.13898v12026
SKILL: Self-correcting Knowledge-guided Iterative Large Language Model Agent for Logic Optimization
Rui Yang
cs.AIarXiv:2608.14579v12026
Longitudinal and Graph-Augmented Prediction of Adolescent Substance Use Onset in the ABCD Study
Yixuan He, Jinni Su, Yun Kang
cs.AIcs.CYcs.LGarXiv:2608.14578v12026
Squeeze-Release: Iterative Pruning with Exact Structural Minimization
Roman Denkin, Ida Akerholm, Prashant Singh +1
cs.LGcs.AIarXiv:2606.14346v12026
Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings
Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja
cs.CVcs.AIcs.LGarXiv:2606.15134v12026
Selective Synergistic Learning for Video Object-Centric Learning
WonJun Moon, Jae-Pil Heo
cs.CVcs.AIarXiv:2606.15527v12026
When Do Diffusion Models learn to Generate Multiple Objects?
Yujin Jeong, Arnas Uselis, Iro Laina +2
cs.CVcs.AIarXiv:2605.00273v22026
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks
Hongcheng Gao, Hailong Qu, Jingyi Tang +18
cs.AIcs.CLarXiv:2606.09669v22026
Attacks on Machine-Text Detectors Retain Stylistic Fingerprints
Rafael Rivera Soto, Barry Chen, Nicholas Andrews
cs.CLcs.AIcs.LGarXiv:2505.14608v32025
Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital
T. J. Barton, Chris Constantakis, Patti Hauseman +4
cs.AIcs.CEcs.MAarXiv:2604.26091v12026
Thinking with Visual Grounding
Junkai Zhang, Yihe Deng, Kai-Wei Chang +1
cs.AIarXiv:2606.16122v12026
Identifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level
Hannah Cha
cs.CYcs.AIcs.HCarXiv:2608.14692v12026

Artificial Intelligence

MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing

Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State

PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation

Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why

Towards One-to-Many Temporal Grounding

Rethinking Irregular Time Series Forecasting from the Perspective of Basis Functions

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

Lance: Unified Multimodal Modeling by Multi-Task Synergy

Beyond Single Object: Learning 3D Relations with Large Language Models

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

Augmenting Text to Increase Translation Difficulty

More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts

TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration

Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning

ARASH: Adaptive Retrieval And Shot Selection for Tabular Prediction

SkillEffect: Checked Lowering for Memory-Bounded Agent Tools

Authorization Before Context: A Model-Neutral Audience Boundary Against Cross-Audience Memory Leakage in Agentic Systems

Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline

GRIP: Grounded Reasoning via Information-Restricted Premises

Graph Surgery and the Do-Operator: A Precise Correspondence for Acyclic Structural Causal Models

AutoResearch: Insight In, Hallucination Out

SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoning

The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence

Behaviour Is an Incomplete Measure of Reasoning Development: Cross-surface pre-arrival accessibility and the limits of developmental inference in a recurrent-depth reasoner

Auditing Self-Evolution in Financial Agents: Capability Gains, Security Drift, and Execution-Interface Mismatch

Historical Backtesting for Scientific Question Discovery: A Protocol and Astronomy Pilot

Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text

Bounded Semantic Planning and Deterministic Compilation for Reliable Enterprise Text-to-SQL

Training with synthetic data for drone detection in thermal imagery

Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps

Decoupled Temporal Encoding for Generative Recommendation

DeepInsight II: One Trace from Benchmark to Robot

Quipu: A Governed Bitemporal Knowledge Graph Store

Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection

Grading Needs a Rubric, Not Intelligence

Beyond MSE: Rethinking the Evaluation Metric and Benchmarking for Irregular Time Series Forecasting

What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations

Delta2Gamma: Band-Wise Adaptive Contrastive Learning of EEG for Alzheimer's Disease Detection

D$^2$ACCI: A Dual-Loop Diagnostic Protocol for Evidence-Preserving Agent Memory

Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing

Average Distance Approximation for Static Large Graphs

CoAL-RAG: A Complexity-Aware Legal Retrieval-Augmented Generation Method

The Price of Anarchy in Disaggregated Inference

FastMix: Fast Data Mixture Optimization via Gradient Descent

EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video

AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties

Rethinking RAG in Long Videos: What to Retrieve and How to Use It?

A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets

HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing

SKILL: Self-correcting Knowledge-guided Iterative Large Language Model Agent for Logic Optimization

Longitudinal and Graph-Augmented Prediction of Adolescent Substance Use Onset in the ABCD Study

Squeeze-Release: Iterative Pruning with Exact Structural Minimization

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

Selective Synergistic Learning for Video Object-Centric Learning

When Do Diffusion Models learn to Generate Multiple Objects?

SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks

Attacks on Machine-Text Detectors Retain Stylistic Fingerprints

Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital

Thinking with Visual Grounding

Identifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level