Awesome Generative Models
📄
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
Shoubo Hu — most-cited papers & profile · Generative Models
← authors
·
overview
Shoubo Hu
9
papers ·
6
citations
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
2025 · 6 citations
GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning
2025
One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
2025
Top co-authors
Hui-Ling Zhen
· 1
Mingxuan Yuan
· 1
Wei Zhang
· 1
Xinyu Chen
· 1
Topics
Fine-Tuning
Reinforcement Learning
Training Techniques
Model-Based RL
Exploration
RLHF & Alignment
Meta-RL