Tsinghua University

Tsinghua University on Hugging Face Daily Papers: 7 papers, 0 in the top 3 of their day, 0 paper of the day.

1. One-Forcing: Towards Stable One-Step Autoregressive Video Generation 7 upvotes, #42 of 2026-06-01
2. Post-Trained MoE Can Skip Half Experts via Self-Distillation 30 upvotes, #10 of 2026-05-19
3. KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration 37 upvotes, #9 of 2026-05-19
4. 4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding 17 upvotes, #17 of 2026-05-11
5. Meta-CoT: Enhancing Granularity and Generalization in Image Editing 25 upvotes, #5 of 2026-04-29
6. OmniAlpha: A Sequence-to-Sequence Framework for Unified Multi-Task RGBA Generation 12 upvotes, #15 of 2025-11-26
7. Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention 22 upvotes, #12 of 2025-10-09

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.