Awesome Multimodal
📄
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
Yuexiang Xie — most-cited papers & profile · Multimodal
← authors
·
overview
Yuexiang Xie
8
papers ·
145
citations ·
18
h-index
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
2025 · 68 citations
On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
2025 · 68 citations
AgentScope: A Flexible yet Robust Multi-Agent Platform
2024 · 9 citations
On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
2026
Agentscope 1.0: A Developer-centric Framework For Building Agentic Applications
2025
On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
2025
Topics
cs.AI
Fine-Tuning
off-policy
on-policy
cs.LG
Policy Gradient
RLHF & Alignment
Offline RL
Reinforcement Learning
Training Techniques