Awesome AI Agents
📄
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
Xiangxin Zhou — most-cited papers & profile · AI Agents
← authors
·
overview
Xiangxin Zhou
7
papers ·
34
citations ·
6
h-index
Tsinghua University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Defeating the Training-Inference Mismatch via FP16
2025 · 34 citations
Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning
2026
Defeating the Training-Inference Mismatch via FP16
2025
Topics
Reinforcement Learning
RLHF & Alignment
Policy Gradient
Value-Based
In-Context Learning
Training Techniques
Fine-Tuning
Code
Efficiency