AI Research Papers
Explore the latest research papers from arXiv in artificial intelligence, machine learning, and related fields. Discover cutting-edge research from top institutions and researchers worldwide. Total: 27748 papers — Page 62 of 555
VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift
Oct 21, 2026
1 authors
cs.CRcs.CLcs.LG+1
AtomicRL: Atomic Reinforcement Learning for Long-Horizon Robotic Manipulation
Oct 21, 2026
10 authors
cs.ROcs.AIcs.CV
Differentially Private Sparse Reward Estimation with Preference Feedback
Oct 21, 2026
5 authors
cs.LGcs.AI
Did the Problem Actually Get Harder? Testing LLMs on Paired P and NP-Complete Problems Hardened by Adversarial Multi-Agent Rewriting
Oct 21, 2026
5 authors
cs.CL
BatchBench: Benchmarking AI Robustness to Batch Effects and Domain Shift in Biomedical Images - A JUMP Cell Painting Leaderboard
Oct 21, 2026
3 authors
cs.LGcs.AI
Velocity Ambiguity Profiles: Time-Resolved Bayes-Risk Diagnostics for Flow Matching
Oct 21, 2026
8 authors
cs.LG
Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use
Oct 21, 2026
17 authors
cs.ROcs.AIcs.CV+2
Minimax Optimality of the NPMLE for Gaussian Mixtures in Hellinger Distance
Oct 21, 2026
2 authors
math.STcs.ITcs.LG
Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research
Oct 21, 2026
12 authors
cs.CLcs.AIcs.CE
The role of locality and weight sharing in convolutional neural networks
Oct 21, 2026
2 authors
cs.LGcond-mat.dis-nncond-mat.stat-mech+1
Self-normalized Bernstein Inequalities for Regenerative Processes and Applications to Learning Without Independence
Oct 21, 2026
2 authors
cs.LGmath.PRmath.ST
Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation
Oct 21, 2026
5 authors
cs.IRcs.AIcs.CL+1
MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems
Oct 20, 2026
8 authors
cs.CRcs.AIcs.CL
DIVE: Benchmarking Full-Duplex Interaction with Visual Engagement in Continuous Streams
Oct 20, 2026
3 authors
cs.AI
The Instruction Tax on Factual Recall: Base Models Can Beat Their Instruction-Tuned Counterparts
Oct 20, 2026
2 authors
cs.CLcs.AI
Rewards for Budget-Aware Multi-Turn Agents That Adapt to Arbitrary Test-Time Constraints
Oct 20, 2026
5 authors
cs.LGcs.AI
A Multi-Agent Framework for Automated Machine Learning with Evidence-based Planning for Medical Image Analysis
Oct 20, 2026
2 authors
cs.CV
Brain2Vec: A Self-Supervised 3D Foundation Model for Structural Brain MRI
Oct 20, 2026
7 authors
cs.CVcs.AIcs.LG
Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V
Oct 20, 2026
5 authors
cs.CVcs.AI
DISTRACT: Degradation-Indexed Study of Textual Reference Across Competing Targets
Oct 20, 2026
2 authors
cs.CVcs.AIcs.LG
WorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution
Oct 20, 2026
6 authors
cs.CVcs.AI
After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents
Oct 20, 2026
6 authors
cs.CRcs.AI
Region-Specific EEG Classification of Hypnotic Susceptibility Using a Sliding-Window 2D CNN: A Subject-Independent Evaluation
Oct 20, 2026
2 authors
cs.LG
Plausible Future, Wrong Choice: Steering World-Action Models toward Intended Future
Oct 20, 2026
14 authors
cs.ROcs.AI
Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity
Oct 20, 2026
8 authors
cs.AI
CNN-based classifier for subject-independent MBTI Extraversion/Introversion preference classification from short-time EEG signals
Oct 20, 2026
2 authors
cs.LG
MythoSemantic: An Interactive System for Discovering Semantic Parallels Across Mythological and Religious Traditions
Oct 20, 2026
4 authors
cs.CL
Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization
Oct 20, 2026
6 authors
cs.AIcs.CLcs.MA
A Bochner Weitzenböck Decomposition for Cellular Sheaf Laplacians, Curvature and Neural Sheaf Diffusion
Oct 20, 2026
4 authors
cs.CGcs.LG