Penghui Qi

17 papers A* 4Journal 12Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
Rethinking the Trust Region in LLM Reinforcement Learning.
CoRR
Penghui Qi, Xiangxin Zhou, Zichen Liu, Tianyu Pang, Chao Du, Min Lin, Wee Sun Lee
2026 J jnl
Revisiting Parameter Server in LLM Post-Training.
CoRR
Xinyi Wan, Penghui Qi, Guangxing Huang, Chaoyi Ruan, Min Lin, Jialin Li
2025 — conf
Balancing Pipeline Parallelism with Vocabulary Parallelism.
MLSys
Man Tsung Yeung, Penghui Qi, Min Lin, Xinyi Wan
2025 J jnl
Defeating the Training-Inference Mismatch via FP16.
CoRR
Penghui Qi, Zichen Liu, Xiangxin Zhou, Tianyu Pang, Chao Du, Wee Sun Lee, Min Lin
2025 J jnl
Optimizing Anytime Reasoning via Budget Relative Policy Optimization.
CoRR
Penghui Qi, Zichen Liu, Tianyu Pang, Chao Du, Wee Sun Lee, Min Lin
2025 A* conf
PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization.
ICML
Xinyi Wan, Penghui Qi, Guangxing Huang, Min Lin, Jialin Li
2025 J jnl
PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization.
CoRR
Xinyi Wan, Penghui Qi, Guangxing Huang, Jialin Li, Min Lin
2025 J jnl
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning.
CoRR
Bo Liu, Leon Guertler, Simon Yu, Zichen Liu, Penghui Qi, Daniel Balcells, Mickel Liu, Cheston Tan, Weiyan Shi, Min Lin, Wee Sun Lee, Natasha Jaques
2025 J jnl
Understanding R1-Zero-Like Training: A Critical Perspective.
CoRR
Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, Min Lin
2024 J jnl
Balancing Pipeline Parallelism with Vocabulary Parallelism.
CoRR
Man Tsung Yeung, Penghui Qi, Min Lin, Xinyi Wan
2024 A* conf
Pipeline Parallelism with Controllable Memory.
NeurIPS
Penghui Qi, Xinyi Wan, Nyamdavaa Amar, Min Lin
2024 J jnl
Pipeline Parallelism with Controllable Memory.
CoRR
Penghui Qi, Xinyi Wan, Nyamdavaa Amar, Min Lin
2024 A* conf
Zero Bubble (Almost) Pipeline Parallelism.
ICLR
Penghui Qi, Xinyi Wan, Guangxing Huang, Min Lin
2024 J jnl
Zero Bubble Pipeline Parallelism.
CoRR
Penghui Qi, Xinyi Wan, Guangxing Huang, Min Lin
2021 A* conf
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II.
ICML
Xiangjun Wang, Junxiao Song, Penghui Qi, Peng Peng, Zhenkun Tang, Wei Zhang, Weimin Li, Xiongjun Pi, Jujie He, Chao Gao, Haitao Long, Quan Yuan
2020 J jnl
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II.
CoRR
Xiangjun Wang, Junxiao Song, Penghui Qi, Peng Peng, Zhenkun Tang, Wei Zhang, Weimin Li, Xiongjun Pi, Jujie He, Chao Gao, Haitao Long, Quan Yuan
2019 J jnl
Artificial Intelligence for Prosthetics - challenge solutions.
CoRR
Lukasz Kidzinski, Carmichael F. Ong, Sharada Prasanna Mohanty, Jennifer L. Hicks, Sean F. Carroll, Bo Zhou, Hongsheng Zeng, Fan Wang, Rongzhong Lian, Hao Tian, Wojciech Jaskowski, Garrett Andersen, Odd Rune Lykkebø, Nihat Engin Toklu, Pranav Shyam, Rupesh Kumar Srivastava, Sergey Kolesnikov, Oleksii Hrinchuk, Anton Pechenko, Mattias Ljungström, Zhen Wang, Xu Hu, Zehong Hu, Minghui Qiu, Jun Huang, Aleksei Shpilman, Ivan Sosin, Oleg Svidchenko, Aleksandra Malysheva, Daniel Kudenko, Lance Rane, Aditya Bhatt, Zhengfei Wang, Penghui Qi, Zeyang Yu, Peng Peng, Quan Yuan, Wenxin Li, Yunsheng Tian, Ruihan Yang, Pingchuan Ma, Shauharda Khadka, Somdeb Majumdar, Zach Dwiel, Yinyin Liu, Evren Tumer, Jeremy D. Watson, Marcel Salathé, Sergey Levine, Scott L. Delp