Shengyi Huang - RankMe

26 papers A* 4C 1Misc 1Journal 20

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	2 OLMo 2 Furious. CoRR Team OLMo, Pete Walsh, Luca Soldaini, Dirk Groeneveld, Kyle Lo, Shane Arora, Akshita Bhagia, Yuling Gu, Shengyi Huang, Matt Jordan, Nathan Lambert, Dustin Schwenk, Oyvind Tafjord, Taira Anderson, David Atkinson, Faeze Brahman, Christopher Clark, Pradeep Dasigi, Nouha Dziri, Michal Guerquin, Hamish Ivison, Pang Wei Koh, Jiacheng Liu, Saumya Malik, William Merrill, Lester James V. Miranda, Jacob Morrison, Tyler Murray, Crystal Nam, Valentina Pyatkin, Aman Rangapur, Michael Schmitz, Sam Skjonsberg, David Wadden, Christopher Wilhelm, Michael Wilson, Luke Zettlemoyer, Ali Farhadi, Noah A. Smith, Hannaneh Hajishirzi
2025	A*	`conf`	Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models. ICLR Michael Noukhovitch, Shengyi Huang, Sophie Xhonneux, Arian Hosseini, Rishabh Agarwal, Aaron C. Courville
2025	J	`jnl`	Generalizing Verifiable Instruction Following. CoRR Valentina Pyatkin, Saumya Malik, Victoria Graf, Hamish Ivison, Shengyi Huang, Pradeep Dasigi, Nathan Lambert, Hannaneh Hajishirzi
2025	J	`jnl`	Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning. CoRR Zihe Liu, Jiashun Liu, Yancheng He, Weixun Wang, Jiaheng Liu, Ling Pan, Xinyu Hu, Shaopan Xiong, Ju Huang, Jian Hu, Shengyi Huang, Siran Yang, Jiamang Wang, Wenbo Su, Bo Zheng
2024	J	`jnl`	Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models. CoRR Michael Noukhovitch, Shengyi Huang, Sophie Xhonneux, Arian Hosseini, Rishabh Agarwal, Aaron C. Courville
2024	A*	`conf`	Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform. ICLR Shengyi Huang, Jiayi Weng, Rujikorn Charakorn, Min Lin, Zhongwen Xu, Santiago Ontañón
2024	J	`jnl`	Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning. CoRR Shengyi Huang, Quentin Gallouédec, Florian Felten, Antonin Raffin, Rousslan Fernand Julien Dossa, Yanxiao Zhao, Ryan Sullivan, Viktor Makoviychuk, Denys Makoviichuk, Mohamad H. Danesh, Cyril Roumégous, Jiayi Weng, Chufan Chen, Md Masudur Rahman, João G. M. Araújo, Guorui Quan, Daniel Tan, Timo Klein, Rujikorn Charakorn, Mark Towers, Yann Berthelot, Kinal Mehta, Dipam Chakraborty, Arjun KG, Valentin Charraut, Chang Ye, Zichen Liu, Lucas N. Alegre, Alexander Nikulin, Xiao Hu, Tianlin Liu, Jongwook Choi, Brent Yi
2024	J	`jnl`	The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization. CoRR Shengyi Huang, Michael Noukhovitch, Arian Hosseini, Kashif Rasul, Weixun Wang, Lewis Tunstall
2024	J	`jnl`	TÜLU 3: Pushing Frontiers in Open Language Model Post-Training. CoRR Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, Noah A. Smith, Yizhong Wang, Pradeep Dasigi, Hannaneh Hajishirzi
2023	J	`jnl`	Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform. CoRR Shengyi Huang, Jiayi Weng, Rujikorn Charakorn, Min Lin, Zhongwen Xu, Santiago Ontañón
2023	A*	`conf`	Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks. NeurIPS Ryan Sullivan, Akarsh Kumar, Shengyi Huang, John P. Dickerson, Joseph Suarez
2023	J	`jnl`	Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks. CoRR Ryan Sullivan, Akarsh Kumar, Shengyi Huang, John P. Dickerson, Joseph Suarez
2023	J	`jnl`	Zephyr: Direct Distillation of LM Alignment. CoRR Lewis Tunstall, Edward Beeching, Nathan Lambert, Nazneen Rajani, Kashif Rasul, Younes Belkada, Shengyi Huang, Leandro von Werra, Clémentine Fourrier, Nathan Habib, Nathan Sarrazin, Omar Sanseviero, Alexander M. Rush, Thomas Wolf
2022	Misc	`conf`	A Closer Look at Invalid Action Masking in Policy Gradient Algorithms. FLAIRS Shengyi Huang, Santiago Ontañón
2022	J	`jnl`	A2C is a special case of PPO. CoRR Shengyi Huang, Anssi Kanervisto, Antonin Raffin, Weixun Wang, Santiago Ontañón, Rousslan Fernand Julien Dossa
2022	J	`jnl`	CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms. J. Mach. Learn. Res. Shengyi Huang, Rousslan Fernand Julien Dossa, Chang Ye, Jeff Braga, Dipam Chakraborty, Kinal Mehta, João G. M. Araújo
2022	A*	`conf`	EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine. NeurIPS Jiayi Weng, Min Lin, Shengyi Huang, Bo Liu, Denys Makoviichuk, Viktor Makoviychuk, Zichen Liu, Yufan Song, Ting Luo, Yukun Jiang, Zhongwen Xu, Shuicheng Yan
2022	J	`jnl`	EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine. CoRR Jiayi Weng, Min Lin, Shengyi Huang, Bo Liu, Denys Makoviichuk, Viktor Makoviychuk, Zichen Liu, Yufan Song, Ting Luo, Yukun Jiang, Zhongwen Xu, Shuicheng Yan
2021	J	`jnl`	An Empirical Investigation of Early Stopping Optimizations in Proximal Policy Optimization. IEEE Access Rousslan Fernand Julien Dossa, Shengyi Huang, Santiago Ontañón, Takashi Matsubara
2021	J	`jnl`	CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms. CoRR Shengyi Huang, Rousslan Fernand Julien Dossa, Chang Ye, Jeff Braga
2021	C	`conf`	Gym-µRTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning. CoG Shengyi Huang, Santiago Ontañón, Chris Bamford, Lukasz Grela
2021	J	`jnl`	Gym-μRTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning. CoRR Shengyi Huang, Santiago Ontañón, Chris Bamford, Lukasz Grela
2020	J	`jnl`	A Closer Look at Invalid Action Masking in Policy Gradient Algorithms. CoRR Shengyi Huang, Santiago Ontañón
2020	J	`jnl`	Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games. CoRR Shengyi Huang, Santiago Ontañón
2020	J	`jnl`	Griddly: A platform for AI research in games. CoRR Chris Bamford, Shengyi Huang, Simon M. Lucas
2019	J	`jnl`	Comparing Observation and Action Representations for Deep Reinforcement Learning in MicroRTS. CoRR Shengyi Huang, Santiago Ontañón