Where to Look Matters: On-Policy Self-Distillation for Long-Video Understanding
Paper • 2608.25356 • Published • 19
Huzheng Yang
huzey
AI & ML interests
Computer Vision
Recent Activity
updated a model 5 days ago
huzey/Qwen3.5-9B-MLP-Cache published a model 5 days ago
huzey/Qwen3.5-9B-MLP-Cache upvoted a paper 2 months ago
Where to Look Matters: On-Policy Self-Distillation for Long-Video UnderstandingOrganizations
None yet
upvoted a paper 2 months ago
upvoted a collection 3 months ago
upvoted 2
papers 3 months ago
upvoted 3
papers 11 months ago
Vibe Spaces for Creatively Connecting and Expressing Visual Concepts
Paper • 2512.14884 • Published • 2
Next-Embedding Prediction Makes Strong Vision Learners
Paper • 2512.16922 • Published • 91
Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
Paper • 2512.04926 • Published • 42