About Me

I am currently a Postdoctoral Researcher in Prof. Jürgen Schmidhuber's group at King Abdullah University of Science and Technology (KAUST).

My research interests lie at understanding the principles of intelligence. Recently, I have been focusing on:

  • LLM-based Planning & Reasoning: Developing agents capable of solving long-range tasks.
  • AI for Science: Scientific reasoning ability of large foundation models.
  • Self-Improving Agents: Theoretical frameworks for agents that can self-optimize.

I received my Bachelor's degree in Physics and my Ph.D. in Statistics from the University of Chinese Academy of Sciences (UCAS).

News

  • Oct 2025 "Huxley-Gödel Machine" released on arXiv.
  • Sep 2025 One paper on Interactive Physics Discovery (PhysGym) accepted to NeurIPS 2025.
  • Sep 2025 One paper on Long-form Writing accepted to EMNLP 2025 (Oral, Outstanding Paper Nominated).
  • Jul 2025 One paper on LLM Acceleration (SepLLM) accepted to ICML 2025.
  • Oct 2024 Joined KAUST as a Postdoctoral Researcher in Schmidhuber's Group.

Selected Publications

(* indicates equal contribution)

Huxley Paper
Huxley-Gödel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
Wenyi Wang, Piotr Piękos, Li Nanbo, Firas Laakom, Yimeng Chen, Mateusz Ostaszewski, Mingchen Zhuge, Jürgen Schmidhuber.
arXiv 2025
[Paper] [Code]
PhysGym Paper
PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors
Yimeng Chen, Piotr Piękos, Mateusz Ostaszewski, Firas Laakom, Jürgen Schmidhuber.
NeurIPS 2025
[Paper] [Code]
Beyond Outlining Paper
Beyond Outlining: Heterogeneous recursive planning for adaptive long-form writing with language models
Ruibin Xiong*, Yimeng Chen*, Dmitrii Khizbullin, Mingchen Zhuge, Jürgen Schmidhuber.
EMNLP 2025 Oral Outstanding Paper Nominated
[Paper] [Code]
OOD Generalization Paper
Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization
Yimeng Chen, Tianyang Hu, Fengwei Zhou, Zhenguo Li, and Zhiming Ma.
ICML 2023
[Paper]
Group Invariant Learning Paper
When Does Group Invariant Learning Survive Spurious Correlations?
Yimeng Chen, Ruibin Xiong, Zhiming Ma and Yanyan Lan.
NeurIPS 2022 Spotlight
[Paper] [Code]
IJCAI 2020 Paper
Evaluating Natural Language Generation via Unbalanced Optimal Transport
Yimeng Chen, Yanyan Lan, Ruibin Xiong, Liang Pang, Zhiming Ma and Xueqi Cheng.
IJCAI 2020
[Paper] [Code]

Work Experience

Postdoctoral Researcher Oct 2024 - Present
King Abdullah University of Science and Technology (KAUST)
Advisor: Prof. Jürgen Schmidhuber
Senior Algorithm Engineer Aug 2023 - Oct 2024
Research Center for Data Storage, Huawei Inc.
Research Intern (AI Theory) Apr 2022 - Apr 2023
Huawei Noah's Ark Lab

Education

Ph.D. in Statistics Sep 2018 - June 2023
University of Chinese Academy of Sciences (UCAS)
Advisor: Prof. Zhiming Ma & Prof. Yanyan Lan
B.S. in Physics Sep 2014 - June 2018
University of Chinese Academy of Sciences (UCAS)
Advisor: Prof. Hong Ding

Honors & Awards

  • CAS Dean Scholarship (2020)
  • UCAS Merit Student (2014-2016, 2019-2020)
  • UCAS Academic Scholarship (2014-2016)