Fangyun Wei
Fangyun Wei on Hugging Face Daily Papers: 13 papers, 3 in the top 3 of their day, 333 upvotes.
- APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation 31 upvotes, #22 of 2026-10-15
- LensErase: A Foundation Model for Erase Anything 52 upvotes, #12 of 2026-10-15
- VibeEdit: Image Editing with Canvas Instructions 23 upvotes, #26 of 2026-10-09
- From Prompting to Composing: A Spatial Canvas Interface for Poster Generation 16 upvotes, #36 of 2026-10-09
- Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models 107 upvotes, #3 of 2026-05-25
- InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation 34 upvotes, #10 of 2026-05-18
- Spatia: Video Generation with Updatable Spatial Memory 28 upvotes, #3 of 2025-12-26
- Animate Any Character in Any World 10 upvotes, #16 of 2025-12-22
- VideoVLA: Video Generators Can Be Generalizable Robot Manipulators 3 upvotes, #23 of 2025-12-09
- From Virtual Games to Real-World Play 10 upvotes, #13 of 2025-06-24
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test 4 upvotes, #22 of 2025-03-10
- EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty 20 upvotes, #4 of 2024-01-29
- AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collections 21 upvotes, #3 of 2023-09-06
Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.