Welcome!

I am currently a Machine Learning Researcher at Apple AI/ML (MLR). Prior to joining Apple, I was a Research Scientist at Meta AI (FAIR Labs). I am based in New York City.

I obtained my Ph.D. degree at the department of Electrical and Electronic Engineering, University of Hong Kong in 2018 and I was supervised by Prof. Victor O.K. Li. My doctoral work explored efficient neural machine translation systems. I also spent a wonderful time visiting the CILVR Lab, New York University working with Prof. Kyunghyun Cho. Before that, I obtained my Bachelor’s degree at the Electronic Engineering Department, Tsinghua University in 2014.

Research Interests

My research interests cover both representation learning and generative models for multiple modalities, including natural languages, images, 3D and speech.

Specifically, I am focusing on developing multi-modal generative models that are efficient, controllable, and adaptive – bridging ML/NLP/CV research and real-time applications. Rather than focusing on scaling the existing architectures, my research aims to simultaneously innovate in the design of separate customized generators, positioning them in the middle of Large Language Models (LLMs)’ interaction with the real world. The customized generative model empowers the LLM-based AI agents, providing enhanced capabilities for generating high-quality data essential for the agent’s learning and planning, as well as augmenting the AI agent’s capacity for effective real-world communication.