LIU Shih-yang

LIU Shih-yang on Hugging Face Daily Papers: 4 papers, 1 in the top 3 of their day, 275 upvotes.

1. GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization 191 upvotes, #1 of 2026-01-09
2. DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning 15 upvotes, #15 of 2025-10-20
3. EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation 6 upvotes, #14 of 2024-10-29
4. LLM-FP4: 4-Bit Floating-Point Quantized Transformers 14 upvotes, #8 of 2023-10-26

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.