Pengyu Cheng

Pengyu Cheng on Hugging Face Daily Papers: 5 papers, 2 in the top 3 of their day, 264 upvotes.

1. Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills 47 upvotes, #2 of 2026-07-27
2. Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills 48 upvotes, #4 of 2026-03-30
3. CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR 5 upvotes, #18 of 2026-03-12
4. Search Self-play: Pushing the Frontier of Agent Capability without Supervision 15 upvotes, #12 of 2025-10-24
5. Kimi-VL Technical Report 113 upvotes, #1 of 2025-04-11

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.