About me

My name is Ethan (Yusheng) Su. I am a research scientist at AMD GenAI team (is hiring 🔥) and work on foundation models, especially focusing on pre-training/post-training framework and training efficiency optimization. Before I joined AMD, I was a Postdoctoral Researcher hosted by Eric Xing from CMU / MBZUAI. I completed my Ph.D. in Department of Computer Science and Technology at Tsinghua University. Throughout my Ph.D. (from 2019 to 2023), I had the privilege of being advised by Zhiyuan Liu and being a part of the THUNLP Lab hosted by Maosong Sun. Besides, I worked closely with some LLM start-up teams, including ModelBest. [CV]

Research

My recent work focuses on LLMs, particularly in post-training (SFT/RL). Specifically, I focus on: (1) scaling training scale by optimizing frameworks, (2) improving efficiency, and (3) maintaining accuracy by addressing training–inference discrepancies (e.g., log-probability mismatches) [Google Scholar] [GitHub] [CV].

Talks

• [Mar. 2024] Invited Research Talk at Microsoft Research - AI Frontiers hosted by Guoqing Zheng. Topic: Efficient Tuning of Large-scale Pre-trained Language Models (LLMs) [slide]
• [Feb. 2024] Invited Research Talk at Microsoft Research - Semantic Machines hosted by Ben Van Durme. Topic: Next-Generation Co-pilot: From Assistant Agent to Autonomy Agent [slide]
• [Jan. 2024] Invited Research Talk at Alibaba DAMO Academy hosted by Ting-En Lin. Topic: From Assistant Agents (Co-pilots) to Autonomous Agents [slide]
• [Jul. 2023] Invited Research Talk at CMU/MBZUAI hosted by Eric P. Xing. Topic: Efficient Adaptation of Large-scale Pre-trained Language Models [slide].

News

• [Aug. 2025] Thrilled to announce that APRIL was released and its Github
• [Aug. 2025] Thrilled to announce that we create the rlsys dockerhub to support AMD MI-series GPUs on the RL training framework.
• [July. 2025] Thrilled to announce that I integrated AMD ROCm support into slime - Blog, Blog, PR, and Docker.
• [Mar. 2025] Thrilled to announce that I integrated AMD ROCm support into verl.
• [Jan. 2025] Thrilled to announce that Agen Laboratory was released and reward 3.9k stars on Github.
• [Sep. 2024] Andrew Ng highlights our work - ChatDev at Sequoia Capital talk.
• [Aug. 2024] Joined AMD GenAI team. We are hiring 🔥.

Publications

• APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation
  Yusheng Su^*, Yuzhen Zhou, Jiajun Li, Gowtham Ramesh, Zilin Zhu, Xiang Long, Chenyang Zhao, Jin Pan, Xiaodong Yu, Ze Wang, Kangrui Du, Jialian Wu, Ximeng Sun, Jiang Liu, Qiaolin Yu, Hao Chen, Zicheng Liu, Emad Barsoum ArXiv 2025. [pdf] [code]

• Agent Laboratory: Using LLM Agents as Research Assistants
  Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Zicheng Liu, Emad Barsoum
  EMNLP 2025. [pdf] [code]

• Tool Learning with Foundation Models
  Yujia Qin, Shengding Hu, Yankai Lin, Weize Chen, Ning Ding, Ganqu Cui, Zheni Zeng, Yufei Huang, Chaojun Xiao, Chi Han, Yi Ren Fung, Yusheng Su, Huadong Wang, Cheng Qian, Runchu Tian, Kunlun Zhu, Shihao Liang, Xingyu Shen, Bokai Xu, Zhen Zhang, Yining Ye, Bowen Li, Ziwei Tang, Jing Yi, Yuzhang Zhu, Zhenning Dai, Lan Yan, Xin Cong, Yaxi Lu, Weilin Zhao, Yuxiang Huang, Junxi Yan, Xu Han, Xian Sun, Dahai Li, Jason Phang, Cheng Yang, Tongshuang Wu, Heng Ji, Zhiyuan Liu, Maosong Sun
  ACM 2025. [pdf] [code]

• ChatDev Communicative agents for software development
  Chen Qian, Xin Cong, Cheng Yang, Weize Chen, Yusheng Su, Juyuan Xu, Zhiyuan Liu, Maosong Sun
  ACL 2024. [pdf] [code]

• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents
  Yusheng Su^*, Weize Chen^*, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chen Qian, Chi-Min Chan, Yujia Qin, Yaxi Lu, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou ( ^* indicates equal contribution)
  ICLR 2024. [pdf] [code]

• ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
  Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, Zhiyuan Liu
  ICLR 2024. [pdf] [code]

• Exploring the Impact of Model Scaling on Parameter-efficient Tuning Methods
  Yusheng Su, Chi-Min Chan, Jiali Cheng, Yujia Qin, Yankai Lin, Shengding Hu, Zonghan Yang, Ning Ding, Xingzhi Sun, Guotong Xie, Zhiyuan Liu, Maosong Sun
  EMNLP 2023. [pdf] [code]

• Parameter-efficient Fine-tuning of Large-scale Pre-trained Language Models
  Ning Ding, Yujia Qin, Guang Yang, Fuchao Wei, Zonghan Yang, Yusheng Su, Shengding Hu, Yulin Chen, Chi-Min Chan, Weize Chen, Jing Yi, Weilin Zhao, Xiaozhi Wang, Zhiyuan Liu, Hai-Tao Zheng, Jianfei Chen, Yang Liu, Jie Tang, Juanzi Li, Maosong Sun.
  Nature Machine Intelligence 2023 (Cover Article). [pdf] [code]

• On Transferability of Prompt Tuning for Natural Language Processing
  Yusheng Su, Xiaozhi Wang, Yujia Qin, Chi-Min Chan, Yankai Lin, Zhiyuan Liu, Peng Li, Juanzi Li, Lei Hou, Maosong Sun, Jie Zhou
  NAACL 2022 (Oral). [pdf] [code] [BibTex] [slide] [video]

• Knowledge Inheritance for Pre-trained Language Models
  Yujia Qin, Yankai Lin, Jing Yi, Jiajie Zhang, Xu Han, Zhengyan Zhang, Yusheng Su, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou
  NAACL 2022 (Oral). [pdf] [code]

• Exploring Low-dimensional Intrinsic Task Subspace via Prompt Tuning
  Yujia Qin, Xiaozhi Wang, Yusheng Su, Yankai Lin, Ning Ding, Zhiyuan Liu, Juanzi Li, Lei Hou, Peng Li, Maosong Sun, Jie Zhou
  ACL 2022 Findings. [pdf] [code]

• CPM: A large-scale Generative Chinese Pre-trained Language Model
  Zhengyan Zhang, Xu Han, Hao Zhou, Pei Ke, Yuxian Gu, Deming Ye, Yujia Qin, Yusheng Su, Haozhe Ji, Jian Guan, Fanchao Qi, Xiaozhi Wang, Yanan Zheng, Guoyang Zeng, Huanqi Cao, Shengqi Chen, Daixuan Li, Zhenbo Sun, Zhiyuan Liu, Minlie Huang, Wentao Han, Jie Tang, Juanzi Li, Xiaoyan Zhu, Maosong Sun
  AI OPEN 2021. [pdf] [code]

• CSS-LM: A Contrastive Framework for Semi-supervised Fine-tuning of Pre-trained Language Models
  Yusheng Su, Xu Han, Yankai Lin, Zhengyan Zhang, Zhiyuan Liu, Peng Li, Maosong Sun
  WWW 2021 Workshop, IEEE/TASLP 2021. [pdf] [code] [slide]

• CokeBERT: Contextual Knowledge Selection and Embedding Towards Enhanced Pre-Trained Language Models
  Yusheng Su, Xu Han, Zhengyan Zhang, Peng Li, Zhiyuan Liu, Yankai Lin, Jie Zhou, Maosong Sun
  EMNLP 2020 Findings, AI OPEN 2021. [pdf] [pdf] [code]

Efficient Training Projects

• (Leader) slime (ROCM version) SGLang-based scalable efficient RL framework. [Blog], [PR], [Docker]

• (Collaborator) verl, (Leader) VeRL-AMD (ROCM version). Efficient scalable RLHF framework to build O1/R1-series models. [code] [blog]

• (Leader/Co-leader) Prompt Transferability. This system assists users in building a prompt bank, allowing them to save well-trained prompts. It also enables swift access and reuse of these prompts whenever the user requires them on unseen tasks and heterogeneous models.

Agents Projects

• (Leader/Co-leader) Agent Laboratory. Agent Laboratory [pdf] [code].

• (Leader/Co-leader) AgentVerse. AgentVerse provides a framework that streamlines the process of developing custom multi-agent systems using LLMs in user-defined environments. This facilitates the design of more efficient multi-agent systems that can be applied to real-world applications. [NVIDIA’s Official Bolg], [Youtube1], [Youtube2]

• (Member) XAgent. XAgent makes more effective decisions and executes efficient actions to accomplish tasks with an unprecedented degree of autonomy. [Youtube1], [Youtube2]

• (Member) ChatDev. ChatDev creates customized software using natural language ideas through LLM-powered multi-agent collaboration. [Youtube1], [Youtube2], [Andrew Ng highlights our work at Sequoia Capital talk]

• (Member) Tool Learning. Tool learning for LLMs, open-source solutions of ChatGPT-Plugins.

LLM Pre-training Projects

• (Member) CPM-X. The first chinese-version large-scale pre-trained project and released a series of LLMs in 2020-2021.

Experiences

Sailing Lab - CMU (U.S) & MBZUAI (U.A.E), 2023 - 2024

• Postdoctoral Researcher
• Advised and hosted by Eric P. Xing

THUNLP Lab - Tsinghua University (China), 2019 - 2023

• Ph.D
• Advised by Zhiyuan Liu
• Hosted by Maosong Sun

MediaTek (Taiwan), 2018 - 2019

• Deep/Machine Learning Engineer Intern
• Advised by Jing-Han Wang.

Microsoft, 2015 - 2016

• Research and Development Intern
• Advised by Kuang-Chao Yeh and Gordon Chang.

Professional Services

Area Chair (Since 2025): ACL

Reviewer (Since 2021): ACL, NAACL, AACL, ACL Roling, EMNLP, COLING, ICLR, ICML, IJCAI, AAAI, NeurIPS

Student Mentoring / Collaboration

• (Since 2024-) Samuel Schmidgall: Johns Hopkins University (PhD) -> Google Deepmind
• (Since 2021-2023) Chi-Min Chan: Tsinghua University (BS) -> Hong Kong University of Science and Technology (HKUST) (PhD)
• (Since 2022-2023) Yu Xia: Peking University (MS) -> Tsinghua University (PhD)
• (Since 2022-2023) Xiuyuan Huang: University of Science and Technology Beijing (BS) -> Peking University (MS)

Vistors