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 148 of 545
Phase-aware video generation for physics-grounded dynamics and interactions
Oct 8, 2026
7 authors
cs.CV
AuraLuxMuse: Adaptive Fusion Modeling for Aesthetic Stage Lighting Design with Music and Expert Guidance
Oct 8, 2026
8 authors
cs.MMcs.AI
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
Oct 8, 2026
8 authors
cs.AIcs.CLcs.CV+1
Softmax Attention on Gaussian Mixtures: Linear When It Can, Selective When It Must
Oct 8, 2026
3 authors
stat.MLcs.LG
From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction
Oct 8, 2026
4 authors
cs.CVcs.AI
Self-Supervised Speech Representations for Cross-Speaker Dysarthria Detection During Awake Craniotomy
Oct 8, 2026
7 authors
cs.LGcs.SDeess.SP
From Suppression to Repair: Mitigating Object Hallucination in Large Vision-Language Models via Localized Distribution Alignment
Oct 8, 2026
8 authors
cs.CVcs.AI
Probability-Signature Dynamics: Unpacking Modular Addition Learning Within Two-Layer Networks
Oct 8, 2026
5 authors
cs.AI
Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing
Oct 8, 2026
3 authors
cs.LGcs.IT
Open-Vocabulary Audio-Visual Event Localization via Complex-Valued Fusion
Oct 8, 2026
5 authors
cs.CVcs.LGcs.MM+2
VEDJE: Video-Efficient Discriminative Joint Encoder for Scalable Video-Text Retrieval
Oct 8, 2026
5 authors
cs.CV
Structural and Representational Agency in LLM-Driven Timbre Generation and Interpolation
Oct 8, 2026
2 authors
cs.SDcs.HCcs.LG+2
DADP: Dynamic Activity-Dependent Pruning, A Reverse Hebbian-Inspired Structural Pruning Method
Oct 8, 2026
1 authors
cs.LG
GRPODropout: Less is More for Online Reinforcement Learning Rollouts
Oct 8, 2026
11 authors
cs.LGcs.AIcs.CL
Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement
Oct 8, 2026
3 authors
cs.CV
Understanding Latent-Dimension Scaling in Dynamical-System Learning through Spectral Reliability
Oct 8, 2026
3 authors
cs.LGmath.DSnlin.CD
Learning structured linear dynamical systems from missing observations
Oct 8, 2026
3 authors
stat.MLcs.LGeess.SY+2
Relative Patch Response Learning for Generalizable AI-Generated Image Detection
Oct 8, 2026
5 authors
cs.CV
How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices
Oct 8, 2026
8 authors
cs.AI
SenseWeather: Multimodal Sensing for Robust Robotic Perception under Extreme Conditions
Oct 8, 2026
7 authors
cs.ROcs.CV
Evaluating Exact Output and Checkpoint-State Prediction in Real Programs
Oct 8, 2026
7 authors
cs.SEcs.AI
Automated Assembly Instruction Generation from CAD Models Using Grounded Large Language Models: A Human-in-the-Loop Framework
Oct 8, 2026
6 authors
cs.LG
Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System
Oct 8, 2026
1 authors
cs.CLcs.AIcs.SE
Can Decision Models Understand Stance? Evaluating Jev Against General-Purpose LLMs
Oct 8, 2026
5 authors
cs.CL
RobustLDS: Learning linear dynamical systems under adversarial corruptions
Oct 8, 2026
2 authors
stat.MLcs.LGeess.SY+2
Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations
Oct 8, 2026
12 authors
cs.CVcs.AI
Not Every Change Is Necessary: Recoverable Drift in Large Language Model Unlearning
Oct 8, 2026
6 authors
cs.CL
From Surface to Depth: Towards Cognitive Appraisal Reasoning in Multimodal Emotion Understanding
Oct 8, 2026
9 authors
cs.MMcs.AIcs.HC
Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents
Oct 8, 2026
8 authors
cs.CL
Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search
Oct 8, 2026
4 authors
cs.IRcs.CL
Revisiting Identity and Spectra Dispersion in Media-Bridged Time Series Forecasting: Linking Multivariate Signals and Narrative Flows
Oct 8, 2026
8 authors
cs.CVcs.LG
EliteTable: Self-Improving Program Search for Executable Control Policies
Oct 8, 2026
1 authors
cs.AIcs.NE
Does Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive Encoders
Oct 8, 2026
2 authors
cs.CV
Efficient Learning of Survival Analysis Models Under Outcome-Dependent Truncation and Censoring
Oct 8, 2026
4 authors
cs.LG
TACROSS: An Efficient and Low-Cost Scalable Human Touch System Across Heterogeneous Tactile Sensors for Dexterous Robot Learning
Oct 8, 2026
14 authors
cs.ROcs.LG