Shengyi Huang

Researcher, Periodic Labs, Inc.

Joined

September 2020

Names

Shengyi Huang (Preferred)

Emails

****@drexel.edu (Confirmed)

****@outlook.com (Confirmed)

****@huggingface.co (Confirmed)

****@allenai.org (Confirmed)

****@periodiclabs.ai

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

Periodic Labs, Inc. (periodiclabs.ai)

2025 – Present

Researcher

Allen Institute for Artificial Intelligence (allenai.org)

2024 – 2025

Researcher

Hugging Face (huggingface.co)

2023 – 2024

PhD student

Drexel University (drexel.edu)

2018 – 2023

Advisors, Relations & Conflicts

PhD Advisor

Santiago Ontañón

2018 – Present

Expertise

deep reinforcement learning

real-time strategy games

2019 – Present

Publications

Tricks or Traps? A Deep Dive into RL for LLM Reasoning
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
- ICLR 2026 Poster
- Readers: Everyone
Generalizing Verifiable Instruction Following
Valentina Pyatkin, Saumya Malik, Victoria Graf, Hamish Ivison, Shengyi Huang, Pradeep Dasigi, Nathan Lambert, Hannaneh Hajishirzi
- NeurIPS 2025 Datasets and Benchmarks Track poster
- Readers: Everyone
2 OLMo 2 Furious (COLM’s Version)
Evan 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, Allyson Ettinger, Michal Guerquin et al. (22 additional authors not shown)
- COLM 2025
- Readers: Everyone
Tulu 3: Pushing Frontiers in Open Language Model Post-Training
Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James Validad Miranda, Alisa Liu, Nouha Dziri, Xinxi Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Christopher Wilhelm, Luca Soldaini, Noah A. Smith et al. (3 additional authors not shown)
- COLM 2025
- Readers: Everyone
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
Michael Noukhovitch, Shengyi Huang, Sophie Xhonneux, Arian Hosseini, Rishabh Agarwal, Aaron Courville
- ICLR 2025 Poster
- Readers: Everyone
Faster, More Efficient RLHF through Off-Policy Asynchronous Learning
Michael Noukhovitch, Shengyi Huang, Sophie Xhonneux, Arian Hosseini, Rishabh Agarwal, Aaron Courville
- FITML 2024 Poster
- Readers: Everyone
Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning
Shengyi Huang, Quentin Gallouédec, Florian Felten, Antonin Raffin, Rousslan Fernand Julien Dossa, Yanxiao Zhao, Ryan Sullivan, Viktor Makoviychuk, Denys Makoviichuk, Mohamad Hosein Danesh, Cyril Roumegous, Jiayi Weng, Chufan Chen, Md Masudur Rahman, João Guilherme Madeira Araújo, Guorui Quan, Daniel Chee Hian Tan, Timo Klein, Rujikorn Charakorn, Mark Towers et al. (13 additional authors not shown)
- Submitted to NeurIPS 2024 Track Datasets and Benchmarks
- Readers: Everyone
Zephyr: Direct Distillation of LM Alignment
Lewis Tunstall, Edward Emanuel 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
- COLM
- Readers: Everyone
The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization
Shengyi Huang, Michael Noukhovitch, Arian Hosseini, Kashif Rasul, Weixun Wang, Lewis Tunstall
- COLM
- Readers: Everyone
The N Implementation Details of RLHF with PPO
Shengyi Huang, Tianlin Liu, Leandro Von Werra
- BT@ICLR2024
- Readers: Everyone

View all 21 publications

Co-Authors

View all 129 co-authors