何建翔 · Jianxiang He
Incoming PhD Student · MBZUAI
Advisor: Prof. Xiaojun Chang (常晓军)
MPhil in AI · HKUST(GZ)
Vision-Language-Action
Embodied AI
World Models
Multimodal LLM
Incoming PhD Student · MBZUAI
Advisor: Prof. Xiaojun Chang (常晓军)
MPhil in AI · HKUST(GZ)
I am a Master of Philosophy student at the Hong Kong University of Science and Technology (Guangzhou), advised by Professor Hui Xiong and Assistant Professor Xuming Hu. My current research focuses on long-video understanding, key-frame selection, and multimodal fusion.
I will join MBZUAI as a PhD student in Fall 2026, under the supervision of Prof. Xiaojun Chang, where I plan to work on Vision-Language-Action (VLA) models, embodied AI, and world models.
Shandong University · 山东大学
B.E. in Automation · NLP, image processing, machine learning
HKUST(GZ) · 香港科技大学（广州）
MPhil in AI · Advisors: Prof. Hui Xiong & Prof. Xuming Hu · Multimodal LLMs, long video
MBZUAI · 穆罕默德·本·扎耶德人工智能大学
PhD in AI · Advisor: Prof. Xiaojun Chang · VLA · Embodied AI · World Models
Unified models grounding language in visual perception and physical actions for robot learning.
Enabling agents to perceive, reason, and act in physical environments through sensorimotor integration.
Internal representations allowing agents to predict, plan, and generalize across scenarios.
Long-video understanding and efficient key-frame selection via multimodal reasoning.
Visitor Locations