Yihan Hu

hadjhab's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article 9 days ago

view article

Article

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

• 

nvidia

•

9 days ago

• 73

upvoted a paper 14 days ago

VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding

Paper • 2605.22907 • Published 20 days ago • 4

upvoted a paper 20 days ago

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

Paper • 2605.15141 • Published 27 days ago • 93

liked a dataset 24 days ago

maifoundations/VideoOdyssey

Viewer • Updated 14 days ago • 100 • 1.12k • 7

upvoted a paper 2 months ago

CutClaw: Agentic Hours-Long Video Editing via Music Synchronization

Paper • 2603.29664 • Published Mar 31 • 50

upvoted 2 papers 6 months ago

PersonaLive! Expressive Portrait Image Animation for Live Streaming

Paper • 2512.11253 • Published Dec 12, 2025 • 41

StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation

Paper • 2512.09363 • Published Dec 10, 2025 • 74

liked a Space 7 months ago

Running

Featured

272

Segment Anything Web

💻

272

Segment objects in images using point prompts