Mengkang Hu 胡梦康

I am a 2nd-year Ph.D. student at The University of Hong Kong (HKU-MMLAB) guided by Prof. Ping Luo (main) and Prof. Wenping Wang.

I am particularly focused on harnessing the potential of Large Language Models (LLMs) to enhance NLP tasks and advance Robotics applications. My current research agenda encompasses: 1. Development and optimization of LLM-based agents (AgentGen, HiAgent); 2. LLM-based planning (Tree-Planner, EmbodiedGPT); 3. Exploration of world modeling capabilities of LLMs (AgentGen).

I am open to research discussions and collaborations, feel free to get in touch at [mkhu at connect dot hku dot hk]!

Email  /  Google Scholar  /  Twitter  /  cv /  cv

profile photo

Selected Publications

HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
Mengkang Hu, Tianxing Chen, Qiguang Chen, Yao Mu, Wenqi Shao, Ping Luo
arXiv 2024
pdf | code
AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
Mengkang Hu, Pu Zhao, Can Xu, Qingfeng Sun, Jianguang Lou, Qingwei Lin, Ping Luo, Saravan Rajmohan, Dongmei Zhang
KDD 2024
pdf
KET-QA: A Dataset for Knowledge Enhanced Table Question Answering
Mengkang Hu, Haoyu Dong, Ping Luo, Shi Han, Dongmei Zhang
COLING 2024
pdf | site
Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
Mengkang Hu, Yao Mu, Xinmiao Yu, Mingyu Ding, Shiguang Wu, Wenqi Shao, Qiguang Chen, Bin Wang, Yu Qiao, Ping Luo
ICLR 2024
pdf | site
EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought
Yao Mu, Qinglong Zhang, Mengkang Hu, Wenhai Wang, Mingyu Ding, Jun Jin, Bin Wang, Jifeng Dai, Yu Qiao, Ping Luo
NeurIPS 2023 (Spotlight)
pdf | code | site

Experience

Research Intern at Shanghai Artificial Intelligence Laboratory
February 2023 - February 2024  |  Shanghai, China

Mainly focus on better use of LLMs in Embodied AI (efficiency, world modeling) under the supervision by Dr. Wenqi Shao.

Research Intern at Microsoft Research Lab – Asia
February 2022 - September 2022  |  Beijing, China

Mainly focus on intersection of TableQA and Knowledge Graph under the supervision of SR. Haoyu Dong and SR. Research Manager Shi Han.

Awards&Service

  • Reviewer of ICLR 2025, KDD 2025 (Research Track)
  • National Scholarship (top 2%), 2021
  • First-Class Scholarship, 2019-2022
  • MSRA Stars of Tomorrow (Award of Excellent Intern), 2022
  • National First Prize in Mathematical Contest in Modeling (top 1%), 2020
  • Mathematical Contest in Modeling, Meritorious Winner, 2020,2021
  • National Third Prize in The 14th International Contest of innovAtioN, 2020

Invited Talks

  • 2024.04.16 Sharing Tree-Planner at RLChina. slides


  • Last update on October 2024.

    Design and source code from Jon Barron's website