Zhenghao Lin

Zhenghao Lin on Hugging Face Daily Papers: 4 papers, 2 in the top 3 of their day, 193 upvotes.

1. Expert-Space Exploration in MoE Reinforcement Learning 5 upvotes, #28 of 2026-09-15
2. Improving Data and Reward Design for Scientific Reasoning in Large Language Models 39 upvotes, #13 of 2026-02-10
3. Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models 40 upvotes, #3 of 2025-01-24
4. Rho-1: Not All Tokens Are What You Need 72 upvotes, #1 of 2024-04-12

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.