Cong Wei

Cong Wei on Hugging Face Daily Papers: 13 papers, 7 in the top 3 of their day, 1,145 upvotes.

1. PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation 31 upvotes, #28 of 2026-10-01
2. VGI-BENCH: Probing Visual Intelligence in Video Generation Models 177 upvotes, #2 of 2026-08-27
3. Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models 107 upvotes, #1 of 2026-07-15
4. Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation 86 upvotes, #2 of 2026-07-15
5. Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction 105 upvotes, #2 of 2026-05-08
6. RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time 100 upvotes, #2 of 2026-04-16
7. Context Forcing: Consistent Autoregressive Video Generation with Long Context 35 upvotes, #6 of 2026-02-06
8. UniVideo: Unified Understanding, Generation, and Editing for Videos 64 upvotes, #5 of 2025-10-10
9. MoCha: Towards Movie-Grade Talking Character Synthesis 103 upvotes, #1 of 2025-04-01
10. VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation 24 upvotes, #5 of 2024-12-03
11. OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision 42 upvotes, #2 of 2024-11-12
12. AnyV2V: A Plug-and-Play Framework For Any Video-to-Video Editing Tasks 17 upvotes, #4 of 2024-03-22
13. ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation 27 upvotes, #6 of 2024-02-08

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.