Penghui Qi

Penghui Qi on Hugging Face Daily Papers: 10 papers, 3 in the top 3 of their day, 285 upvotes.

1. Best Practice Critic Optimization 17 upvotes, #9 of 2026-08-26
2. Rethinking the Divergence Regularization in LLM RL 33 upvotes, #11 of 2026-06-10
3. Rethinking the Trust Region in LLM Reinforcement Learning 30 upvotes, #12 of 2026-02-05
4. Revisiting Parameter Server in LLM Post-Training 7 upvotes, #13 of 2026-01-28
5. Defeating the Training-Inference Mismatch via FP16 27 upvotes, #6 of 2025-11-03
6. Optimizing Anytime Reasoning via Budget Relative Policy Optimization 34 upvotes, #3 of 2025-05-21
7. Understanding R1-Zero-Like Training: A Critical Perspective 36 upvotes, #7 of 2025-04-03
8. PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization 14 upvotes, #9 of 2025-03-05
9. Balancing Pipeline Parallelism with Vocabulary Parallelism 18 upvotes, #3 of 2024-11-11
10. Zero Bubble Pipeline Parallelism 25 upvotes, #3 of 2024-01-22

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.