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
Haibin Lin — most-cited papers & profile · Multimodal
← authors
·
overview
Haibin Lin
12
papers ·
1770
citations ·
11
h-index
Aviation Industry Corporation of China (China) · Shenzhen Academy of Metrology and Quality Inspection · Nanjing University of Aeronautics and Astronautics
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
2025 · 1767 citations
FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
2025 · 3 citations
Laminar: A Scalable Asynchronous RL Post-Training Framework
2025
FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
2025
Robust LLM Training Infrastructure at ByteDance
2025
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
2025
Seed1.5-VL Technical Report
2025
FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
2025
MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production
2025
ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12,000 GPUs
2025
HybridFlow: A Flexible and Efficient RLHF Framework
2024
Topics
RLHF & Alignment
cs.LG
Policy Gradient
cs.DC
Training Techniques
cs.AI
Reinforcement Learning
Value-Based
Safe RL
Model-Based RL