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 195 of 545
UniSlider: Perceptually Uniform Sliders for Continuous Image Editing
Oct 5, 2026
6 authors
cs.CVcs.AIcs.GR
Anatomy-aware Fine-grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report
Oct 5, 2026
15 authors
cs.CV
Learning to Read the Contextual Tokens in Diffusion Transformers
Oct 5, 2026
5 authors
cs.CVcs.AIcs.GR+1
BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance
Oct 5, 2026
3 authors
cs.AI
S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation
Oct 5, 2026
3 authors
cs.CV
InterMimicGen: Scaling Humanoid Loco-Manipulation through Self-Evolving Motion Imitation
Oct 5, 2026
11 authors
cs.ROcs.CVcs.GR
One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline
Oct 5, 2026
6 authors
cs.CVcs.AI
Agent Behavior as Code: Efficient and Robust LLM Agents with Programmatic Specifications
Oct 4, 2026
7 authors
cs.AIcs.CLcs.MA
Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs
Oct 4, 2026
8 authors
cs.CVcs.AI
GRAM: Correcting Frozen Time-Series Foundation Models via Graph-Retrieved Amplitude Memory
Oct 4, 2026
10 authors
cs.LG
Viva La Vida: Verification and Accumulation Failures in Multi-Agent Proof Search
Oct 4, 2026
3 authors
cs.CLcs.AIcs.MA
Cluster Validation Indices as Self-Supervised Objectives for Text Representation Learning
Oct 4, 2026
5 authors
cs.CLcs.AI
Hierarchy-GBP: Accelerating Factor Graph Inference via Abstraction and Recovery
Oct 4, 2026
6 authors
cs.CVcs.LGcs.RO
Which Preferences to Train On? End-to-End Multi-Objective Alignment with an Adversarial Preference Distribution
Oct 4, 2026
3 authors
cs.LG
PIT-GCL: Protein Interaction using Topological Graph Contrastive Learning
Oct 4, 2026
8 authors
cs.LGcs.AI
One Tile, Multiple Instances: Rethinking MIL for Sparse Diagnostic Evidence
Oct 4, 2026
4 authors
cs.CVcs.LG
Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
Oct 4, 2026
6 authors
cs.CRcs.AI
Enhancing Long-Video VLM Embeddings with Query-Aware Streaming Latent Reasoning
Oct 4, 2026
4 authors
cs.CVcs.AI
Greedy Local Learning for Language Model Pretraining: Gaps and Objective Design
Oct 4, 2026
5 authors
cs.LGcs.AI
From Memory to Guide: Spatio-Temporal Composer for Procedural Coding Memory
Oct 4, 2026
7 authors
cs.AI
Your Temporal Link Predictor Is Blind to Who Is Active: A Missing Factor That Transfers Across Models
Oct 4, 2026
6 authors
cs.LGcs.SI
SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
Oct 4, 2026
6 authors
cs.AIcs.CLcs.LG
Bounded Reasoning: Cognitive Hierarchy in Human-versus-AI Cyber Defense
Oct 4, 2026
3 authors
cs.CRcs.HCcs.LG
No Hindsight for LLM Fact-Checkers: Measuring Leakage Channels in Misinformation Detection
Oct 4, 2026
2 authors
cs.CL
ForkPilot: Self-Evolving Policy for Retrospective Search in Long-Horizon Agents
Oct 4, 2026
9 authors
cs.AI
SFlexRCA: Lightweight, Scalable, and Flexible Root Cause Analysis for IIoT Edge Systems
Oct 4, 2026
5 authors
cs.LGcs.AI
A Systematic Analysis of the Predictive Power of LM Surprisal in Reading Chinese
Oct 4, 2026
7 authors
cs.CLcs.AI
Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning
Oct 4, 2026
9 authors
cs.CL
A Data-Driven Framework for Unsupervised Monitoring of Transmission Systems Using End-of-Line Testing Data: A Case Study at Ford Motor Company
Oct 4, 2026
9 authors
cs.LGstat.APstat.CO
ScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection
Oct 4, 2026
8 authors
cs.LGcs.AI
Why Subliminal Learning Needs So Much Data: A Noisy Inverse View through Steering Vector Recovery
Oct 4, 2026
7 authors
cs.LGcs.AI
VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research
Oct 4, 2026
5 authors
cs.AIcs.CV