Chenfeng Xu

Chenfeng Xu on Hugging Face Daily Papers: 10 papers, 2 in the top 3 of their day, 280 upvotes.

1. Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals 3 upvotes, #35 of 2025-06-04
2. Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation 38 upvotes, #12 of 2025-05-28
3. Segment Any Motion in Videos 15 upvotes, #13 of 2025-03-31
4. Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment 2 upvotes, #23 of 2024-12-11
5. Law of Vision Representation in MLLMs 87 upvotes, #1 of 2024-08-30
6. Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment 4 upvotes, #24 of 2024-06-19
7. Looking Backward: Streaming Video-to-Video Translation with Feature Banks 12 upvotes, #8 of 2024-05-28
8. StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation 75 upvotes, #1 of 2023-12-21
9. 3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features 11 upvotes, #8 of 2023-11-09
10. NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection 15 upvotes, #4 of 2023-07-28

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.