*Taken in the KAUST AI Initiative.

Mingchen Zhuge

Currently, I am in my second year as a PhD student at the KAUST AI Initiative. I am fortunate to have Jürgen Schmidhuber as my advisor.

My current research interests and skills include:

  • Multimodal: Multimodal Understanding/Generation; currently prefer video-based settings.
  • LLMs: Training LLMs and domain-specific fine-tuning.
  • Meta Learning: Recursive Self-Improvement.
  • Agent Society: Society of Mind, LLM-based Multi-Agent Systems.

😀 Will Join Meta as Research Scientist Intern in Summer 2024

⭐ Open-source enthusiasts. I am active in open-sourced communities like MetaGPT, GPTSwarm and OpenDevin.

Before joining KAUST, I've worked as an engineer, researcher (or intern) at NSFocus, Alibaba Group, IIAI (G42), SUSTech VIP Lab, and Microsoft.

Description of the image

Selected Publications ( Full list)


Image Description
Language Agents as Optimizable Graphs
Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin and Jürgen Schmidhuber
ICML 2024 (Oral)
Oral Presentation (top 1.5% in 9,473); The first framework emphasizes the importance of graphs in LLM-based agents.
[Paper] [Code] [BibTex] [麻省理工科技评论专访]


Image Description
MetaGPT: Meta Programming For A Multi-Agent Collaborative Framework
Sirui Hong∗, Mingchen Zhuge∗, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu†, Jürgen Schmidhuber
ICLR 2024 (Oral)
Get 40k+ stars on GitHub; Oral Presentation (top 1.2% in 7,262)
[Paper] [Code] [BibTex] [量子位报道]
Image Description
Mindstorms in Natural Language-Based Societies of Mind
Mingchen Zhuge*, Haozhe Liu*, Francesco Faccio*, Dylan R. Ashley*, Róbert Csordás, Anand Gopalakrishnan, Abdullah Hamdi, Hasan Abed Al Kader Hammoud, Vincent Herrmann, Kazuki Irie, Louis Kirsch, Bing Li, Guohao Li, Shuming Liu, Jinjie Mai, Piotr Piękos, Aditya Ramesh, Imanol Schlag, Weimin Shi, Aleksandar Stanić, Wenyi Wang, Yuhui Wang, Mengmeng Xu, Deng-Ping Fan, Bernard Ghanem, Jü̈rgen Schmidhuber
NeurIPS Ro-FoMo (Best Paper Award)
Best Paper Award in NeurIPS Ro-FoMo Workshop; Position Paper;
[Paper] [Code] [BibTex] [Award]


Image Description
Salient Object Detection via Integrity Learning
Mingchen Zhuge*, Deng-Ping Fan*, Nian Liu, Dingwen Zhang, Dong Xu, Ling Shao
TPAMI 2022
ESI Highly Cited Paper
[Paper] [Code] [Poster] [BibTex]


Image Description
Kaleido-BERT: Vision-Language Pre-training on Fashion Domain
Mingchen Zhuge*, Dehong Gao*, Deng-Ping Fan†, Linbo Jin, Ben Chen, Haoming Zhou, Minghui Qiu, Ling Shao
CVPR 2021
Industry Application in alibaba.com
[Paper] [Code] [BibTex] [Talk]


June 2024 - Present

Research Scientist Intern, Meta
Advisor: Changsheng Zhao
Topic: Multimodal LLMs, Agents
Location: Burlingame, United States

Aug 2022 - Present

PhD Student, KAUST AI Initiative
Advisor: Jürgen Schmidhuber
Topic: Multimodal, LLMs, Agent Society, Meta Learning
Location: Thuwal, KSA

May 2022 - Aug 2022

Research Scientist Intern, Microsoft (WizardLM)
Host: Chongyang Tao
Topic: NLP, Multimodal LLM
Location: Beijing, China

Jul 2021 - Jan 2022

Visiting Scholar, SUSTech
Host: Feng Zheng
Topic: Multimodal (Audio-Visual)
Location: Shenzhen, China

Mar 2021 - Jun 2021

Research Intern, IIAI
Host: Deng-Ping Fan, Ling Shao
Topic: Computer Vision
Location: Abu Dhabi, UAE

May 2020 - Feb 2021

Algorithm Intern, Alibaba Group
Host: Dehong Gao
Topic: Multimodal (Vision-Language Pre-training)
Location: Hangzhou, China

March 2018 - Jun 2018

Research Intern, NSFocus
Host: Wenmao Liu
Topic: Blockchain, Network Security
Location: Beijing, China

Invited Talks


Exploring Multimodal Agents
Host: WAIC AI Lite Think Talk  


Host: 中科院自动化所  


NLSOM、MetaGPT、GPTSwarm: 以不一样的视角探索AI智能体
Host: ByteDance  


Host: 华为藤蔓技术论坛2024  


机器之心: "走进全球顶尖实验室第一期-IIAI"
Host: 机器之心 (Synced)