Awesome Reinforcement Learning
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Yuhong Li — most-cited papers & profile · Reinforcement Learning
← authors
·
overview
Yuhong Li
9
papers ·
663
citations ·
12
h-index
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Medusa: Simple LLM Inference Acceleration Framework With Multiple Decoding Heads
2024 · 648 citations
SnapKV: LLM Knows What You are Looking for Before Generation
2024 · 15 citations
Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting
2026
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
2024
Top co-authors
Chao Liu
· 1
Hongqiang Lin
· 1
Nenggan Zheng
· 1
Xiaofan Bai
· 1
Xipeng Cao
· 1
Xuan Jin
· 1
Topics
Efficiency
Model Architecture
Fine-Tuning
Training Techniques
Memory
Evaluation
Benchmarks
Multi-Agent