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 125 of 545
TAG: Calibrating SAM3 for Universal Image Segmentation without Dense Supervision
Oct 10, 2026
5 authors
cs.CV
Prospective Forcing: Learning to Look Ahead for Autoregressive Long Video Diffusion
Oct 10, 2026
9 authors
cs.CVcs.AI
TGuide: Faster Autoregressive Video Diffusion via Historical Trajectory Guidance
Oct 10, 2026
6 authors
cs.CV
SPARE: Shared Perception and Adaptive Retrieval of Evidence for Streaming Video Understanding
Oct 10, 2026
10 authors
cs.CV
Competition Domains Matter: Selective Head Globalization for Training-Free Sparse Attention in Video Diffusion Transformers
Oct 10, 2026
6 authors
cs.CV
CAST-ASD: Causal Attention over Speakers and Time for Online Active Speaker Detection
Oct 10, 2026
4 authors
cs.CVcs.SD
HumanPhys: A Human-Centric Physical-World Perception Benchmark for Real-World Visual Reasoning
Oct 10, 2026
7 authors
cs.CV
A Hybrid Kinematic GCN and Elastic Transformer for Efficient Indian Sign Language Recognition
Oct 10, 2026
3 authors
cs.AIcs.CV
Demiurge: Forging Navigable 4D Worlds via Autoregressive Video Rerendering
Oct 10, 2026
13 authors
cs.CV
One-Way Coupling via Patchwise Adaptive Normalization in Transformer Surrogates
Oct 10, 2026
6 authors
cs.LG
AcrossVAM2.0: Conflict-Aware Point Supervision for Parameter-Efficient Video Diffusion Adaptation
Oct 10, 2026
2 authors
cs.AI
VoTSpeech: Decoupling Voice Design from Speech Generation in Instruction-Following TTS
Oct 10, 2026
7 authors
cs.SDcs.CL
AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generation
Oct 10, 2026
4 authors
cs.SDcs.AI
PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training
Oct 10, 2026
11 authors
cs.CV
DSABench: Benchmarking Source Discovery, Coordination, and Execution for Multi-Database Agents
Oct 10, 2026
3 authors
cs.AI
Towards Merging-conditional Backdoor Unalignment against Large Language Models
Oct 10, 2026
7 authors
cs.CRcs.AIcs.CL
Linear-Time Non-Local Codec Placement for Machine Learning Model Compression
Oct 10, 2026
1 authors
cs.LG
Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine
Oct 10, 2026
18 authors
cs.CLcs.AI
PixARG: Pixel-Asynchronous Retrieval-Augmented Diffusion for Fast and Realistic Image Generation
Oct 10, 2026
4 authors
cs.CV
Multi-Token Random-Walk Learning via Meeting-Triggered Information Exchange
Oct 10, 2026
2 authors
cs.LG
Integrating AIRL-Based Reward Estimation into a Control Method Using Fuzzy Inference and Policy Gradient
Oct 10, 2026
1 authors
cs.LGcs.AI
Self-improving data synthesis enables scalable adaptation of embedding models
Oct 10, 2026
5 authors
cs.IRcs.AIcs.LG
Align-VAE: Aligning Attention and Geometry in VecSet VAEs for 3D Reconstruction
Oct 10, 2026
5 authors
cs.CV
Think in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems
Oct 10, 2026
6 authors
cs.AI
Japanese Handwriting Generation Based on Human Preference Feedback Using Direct Preference Optimization
Oct 10, 2026
4 authors
cs.CV
BridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries
Oct 10, 2026
9 authors
cs.ROcs.CV
More Domains, No Gains? FLO: Fast-Slow Reciprocal Learning for Multi-Domain Graph Pre-training
Oct 10, 2026
5 authors
cs.LG
Equal-information evaluation of credit assignment in modular financial reinforcement learning
Oct 10, 2026
2 authors
cs.AI
GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs
Oct 10, 2026
3 authors
cs.AI
Amharic-English Cross-Language Question Answering Using Statistical Machine Translation, Named Entity Recognition, and Semantic Indexing
Oct 10, 2026
2 authors
cs.CL