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: 27248 papers — Page 248 of 545
Multi-Site Real-World Performance of Commercial AI for Pulmonary and Incidental Pulmonary Embolism Detection
Sep 29, 2026
16 authors
cs.CVcs.AI
Which papyrus HTR is good enough? Character-error-rate tolerance of four papyrological tasks on Greek texts
Sep 29, 2026
2 authors
cs.CL
When Noise Estimation Hides Basis Misspecification in Repeated Bayesian Inverse Problems
Sep 29, 2026
2 authors
stat.MEmath.STstat.ML
OmniVCBench: Benchmarking Evidence-Grounded Multimodal Reasoning Towards AI Virtual Cells
Sep 29, 2026
6 authors
cs.AIq-bio.QM
HiRAE: Hierarchical Representation Autoencoding with Residual Budgets
Sep 29, 2026
8 authors
cs.CVcs.AI
Selecting What Matters: Semantic Compression-Guided Selective Pooling for Long-Context Embeddings
Sep 29, 2026
7 authors
cs.CL
A Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System
Sep 29, 2026
13 authors
cs.CVcs.AI
CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals
Sep 29, 2026
3 authors
cs.CV
Adam under Generalized Smoothness with Second-Moment-Type Stochastic Gradients
Sep 29, 2026
6 authors
cs.AI
A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses
Sep 29, 2026
3 authors
cs.CLcs.AI
Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance
Sep 29, 2026
2 authors
cs.LGcs.AI
A neural network that maintains and retrieves memories based on context
Sep 29, 2026
7 authors
cs.AIcs.NE
GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets
Sep 29, 2026
8 authors
eess.AScs.AIcs.LG+1
Challenges and Solutions for Bandits in the Wild: Warm-Started Mixture Bandits for Cross-Cohort Slate Recommendation
Sep 29, 2026
11 authors
cs.LGcs.AI
ByteTraX: Enhancing the ByteTrack Architecture with Optimised Thresholding
Sep 29, 2026
1 authors
cs.CV
CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data
Sep 29, 2026
2 authors
cs.CLcs.LG
Feedback-Calibrated Protein Optimization with Batch-Aligned Tail Arbitration
Sep 29, 2026
4 authors
cs.LG
Pixel-Level Transformers in Remote Sensing: A Canopy Height Case Study
Sep 29, 2026
5 authors
cs.CVcs.AI
Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents
Sep 29, 2026
6 authors
cs.ROcs.AI
WINGS: Reference-Free Gaussian Splatting Inpainting with 3D-Native Generative Priors
Sep 29, 2026
3 authors
cs.CV
Minkowski Attractor Networks: Closed-Form Hyperbolic Flows for Visual Representations
Sep 29, 2026
1 authors
cs.CV
Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue
Sep 29, 2026
8 authors
cs.CLcs.AI
Making Duplicate Reimbursement Unrepresentable: A Verified Ethereum E-Invoice System for Humans and AI Agents
Sep 29, 2026
1 authors
cs.CRcs.AIcs.CE
Privy to the Foil: Recasting Value Estimation with a Self-Privileged Critic for RLVR
Sep 29, 2026
8 authors
cs.LGcs.AI
ReCaVSR: One-Step Streaming Diffusion Video Super-Resolution with Recycled Latents and Learned Cache Routing
Sep 29, 2026
6 authors
cs.CV
Behavioral Convergence Without Representational Convergence: Persistent Training-History Dependence in Neural Networks
Sep 29, 2026
1 authors
cs.LG
Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety-Helpfulness Alignment
Sep 29, 2026
8 authors
cs.CL
Counterfactual Probing for Parallel Unmasking with Hidden Forest Structure
Sep 29, 2026
3 authors
cs.LGstat.ML
Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection
Sep 29, 2026
3 authors
cs.LGcs.AI
Evaluation Choices Shape Biomedical ML Claims: A Pediatric Pneumonia Benchmark Case Study
Sep 29, 2026
4 authors
cs.CVcs.LG
RelayVSR: Large-Small Model Collaboration for Efficient Real-World Video Super-Resolution
Sep 29, 2026
6 authors
cs.CV
FlowMap-OPD: Rollout--Kernel Separation for On-Policy Distillation of Few-Step Flow-Map Generators
Sep 29, 2026
2 authors
cs.CVcs.LG
AnthroDial: Benchmarking LLM Anthropomorphism in Autonomous Social Interaction
Sep 29, 2026
16 authors
cs.CL
Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability
Sep 29, 2026
5 authors
cs.AI
Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning
Sep 29, 2026
5 authors
cs.LGcs.CL
One Threshold Does Not Fit All Languages: Language-Conditional Deferral for Reliable and Efficient Low-Resource Text Classification
Sep 29, 2026
2 authors
cs.CLcs.LG
It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them
Sep 29, 2026
4 authors
cs.CLcs.AIcs.CV
AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems
Sep 29, 2026
6 authors
cs.SEcs.AI