Kunhang Li

Tokyo, Japan

prof_pic.jpg

Hello from Kun!😄

你好! / Hi! / こんにちは! / Grüß dich!

I am Kunhang Li (李坤航), a Computer Science PhD candidate at Miyao Lab from Graduate School of Information Science and Technology, The University of Tokyo.

My current research interests lie within 3D/4D multimodal understanding and generation, especially language and human motion. My dream is to build a digital universe like The Matrix.

P.S.: I post blogs on roaming, films, research, and random thoughts.
P.P.S.: I track my pace towards a polyglot.

news

Sep 29, 2025 I start a research internship working on human motion generation at Shanda AI Research!
Aug 20, 2025 Our paper on exploring the boundries of LLMs’ human motion understanding is accepted to EMNLP 2025 Findings!
Jun 16, 2025 I start a part-time RA position working on Vision-Language-Action (VLA) models with Prof. Shuhei Kurita at National Institute of Informatics (NII LLMC)! Looking forward to bridging my experience in multimodality and NLP back to my bachelor major (robotics)~
Dec 20, 2024 I start a research internship working on AI-automated scientific research at OMRON SINIC X!
Mar 21, 2024 Our paper on fine-grained text2motion (work done back at Peking University with Prof. Yansong Feng) got accepted by LREC-COLING 2024! Check the project website here!

selected publications

  1. How Much Do Large Language Models Know about Human Motion? A Case Study in 3D Avatar Control
    Kunhang Li, Jason Naradowsky , Yansong Feng , and 1 more author
    In Findings of the Conference on Empirical Methods in Natural Language Processing , 2025
  2. Motion Generation from Fine-grained Textual Descriptions
    Kunhang Li, and Yansong Feng
    In the Joint International Conference on Computational Linguistics, Language Resources and Evaluation , 2024