Fei Zhao

Fei Zhao on Hugging Face Daily Papers: 8 papers, 0 in the top 3 of their day, 144 upvotes.

1. ROSS: Relearning from Self-Generated Rollouts through Selective Supervision 49 upvotes, #21 of 2026-09-30
2. Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation 20 upvotes, #5 of 2026-09-08
3. D^3-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation 25 upvotes, #9 of 2026-08-27
4. QP-OneModel: A Unified Generative LLM for Multi-Task Query Understanding in Xiaohongshu Search 6 upvotes, #28 of 2026-02-12
5. Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training 9 upvotes, #23 of 2026-02-04
6. Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors 8 upvotes, #21 of 2026-02-02
7. RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services 18 upvotes, #9 of 2025-11-11
8. RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services 7 upvotes, #8 of 2025-07-21

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.