I build multimodal foundation models and agents that connect perception, reasoning, world modeling, and action.
A concise research-focused introduction.
I am a PhD student at Nanyang Technological University (NTU), advised by Prof. Jianfei Yang. My research focuses on multimodal foundation models and agents for embodied intelligence, particularly embodied reasoning, vision-language-action models, world models, and robot learning. I received my B.Eng. in Computer Science from Taishan College at Shandong University, where I worked with Prof. Xuemeng Song, and I have been a research assistant at the Intelligent Media Research Center (iLearn), led by Prof. Liqiang Nie. I am also a research intern at Alibaba DAMO Academy, developing open embodied models and systems.
Research appointments and internships.
Research Intern · Embodied Intelligence and World Model
Mentors: Dr. Xin Li, Dr. Jun Cen, and Ronghao Dang.
I also work closely with my talented colleagues Jiayan Guo on agents and Siteng Huang on VLA models.
Research Assistant · Multimodal Large Language Models and Information Retrieval
Supervisors: Prof. Xuemeng Song and Prof. Liqiang Nie.
Academic training and degree programs.
PhD Student
Advised by Prof. Jianfei Yang. Research direction: multimodal learning, MLLM Agents, and embodied intelligence.
B.Eng. in Computer Science and Technology
Taishan College, First-Honor Program. GPA: 88.5 / 100; Rank: 5 / 22.
* Equal or core contribution, as specified by each paper.
A general-purpose robotic value foundation model that learns temporal distance from 7,000+ hours of heterogeneous data, turning time-to-completion into signals for progress estimation, failure detection, and VLA reinforcement learning.
Winner of the WWW’25 Multimodal Document Retrieval Challenge.
Left: visual preview. Right: paper information.
Representative open-source effort.
A popular Chinese knowledge base and resource index for embodied intelligence, organized in an encyclopedia-style format. It covers robotics foundations, robot learning, simulators, benchmarks, datasets, multimodal models, VLA models, navigation, and related embodied-AI research directions.
Compact highlights; link to CV for the full list.
