Tianyuan Wu
Scholar

Tianyuan Wu

Google Scholar ID: NLrqUgIAAAAJ
CSE Department, HKUST
ML SystemsReinforcement Learning
Google Scholar↗
Citations & Impact
All-time
Citations
65
 
H-index
4
 
i10-index
3
 
Publications
9
 
Co-authors
11
list available
Contact
No contact links provided.
Publications
6 items
RollArt: Scaling Agentic RL Training via Disaggregated Infrastructure
2025
Cited
0
RollMux: Phase-Level Multiplexing for Disaggregated RL Post-Training
2025
Cited
0
AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs
2025
Cited
0
RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training
2025
Cited
0
Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
2025
Cited
0
Adaptra: Straggler-Resilient Hybrid-Parallel Training with Pipeline Adaptation
2025
Cited
0
Resume (English only)
Co-authors
11 total
Wei Wang
Wei Wang
The Hong Kong University of Science and Technology
Hanfeng Lu
Hanfeng Lu
HKUST
Qizhen Weng
Qizhen Weng
Hong Kong University of Science and Technology
Xusheng Chen
Xusheng Chen
Huawei Cloud
Minchen Yu
Minchen Yu
The Chinese University of Hong Kong, Shenzhen
Yizhou Shan
Yizhou Shan
Huawei Cloud
Binhang Yuan（袁彬航）
Binhang Yuan（袁彬航）
Hong Kong University of Science and Technology
Peng Cheng
Peng Cheng
Microsoft Research