Awesome AI for Code
📄
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 for Code
← authors
·
overview
Xiangxin Zhou
37
papers ·
91
citations ·
6
h-index
Tsinghua University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Defeating the Training-Inference Mismatch via FP16
2025 · 34 citations
Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process
2024 · 1 citations
Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning
2026
Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
2026
Rethinking the Divergence Regularization in LLM RL
2026
Rethinking the Trust Region in LLM Reinforcement Learning
2026
GEM: A Gym for Agentic LLMs
2025
Reinforcing General Reasoning without Verifiers
2025
Top co-authors
Jiaqi Tang
· 2
Jiarui Yao
· 2
Tianyu Pang
· 2
Bowen Ping
· 1
Chunchao Guo
· 1
Haitao Mi
· 1
Haonan Wang
· 1
Haowei Lin
· 1
Huanjin Yao
· 1
Jianzhu Ma
· 1
Junyao Yang
· 1
Jun Zhang
· 1
Topics
cs.LG
cs.AI
Policy Gradient
cs.CL
RLHF & Alignment
Model-Based RL