Biography

I work on researching and developing new Multimodal Generative AI models.

My research interest includes Deep Learning, Computer Vision, Machine Learning, Multimodal Generative AI, Diffusion Transformer, 3D Deep Learning, Representation Learning, Detection and Segmentation.

I received my M.S. degree in Electrical and Computer Engineering from Carnegie Mellon University and B.Eng. degree in Computer Science and Technology from China University of Geosciences. 

In my free time, I play piano and PlayStation console, raise my Shiba Inu puppy, hiking canyons, and collect artistic keycaps!

Work:

• Apr. 2025 - I joined Google Deepmind as Senior Research Engineer in Mountain View, CA USA.

• Nov 2023 - I joined Google as a Senior Machine Learning Algorithm Engineer at Labs in Mountain View, CA USA.

• Jan 2021 - I joined Apple as a Computer Vision Algorithm Engineer in Cupertino, CA USA.

• July 2019 - I joined Google AI as a Resident in Mountain View CA USA.

• Jan, 2019 - I interned at Nvidia Research in Santa Clara CA USA.

• May, 2018 - I interned at Mitsubishi Electric Research Laboratories in Boston, USA.

• Sep. 2017 - I was a graduate assistant at Machine Learning Department CMU, advised by Prof. Katerina Fragkiadaki and earlier at Cylab Mobility Research Center, CMU Silicon Vally.

• Mar, 2017 - I  interned at National Laboratory of Pattern Recognition, Chinese Academy of Sciences, advised by Prof. Ran He.

Publication:

• Sep 2021 - Our paper "Coupled Segmentation and Edge Learning via Dynamic Graph Propagation"  is accepted at NeurIPS 2021, [link][slides]!

• Dec 2020 - Tensorflow 3D, a codebase for 3d scene understanding is open sourced on Github. [Google AI blog post] [News 1 2 3] 

• July 2020 - Our paper "An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds", ECCV 2020. [arXiv][website][short / long video]

• Sep 2019 - One paper on self-supervised GAN is accepted at WACV 2020![paper]

•  2018  - One paper on online training of detector is accepted at AIPR 2018. [paper]

• July, 2017 - One paper is accepted at ICCV 2017! "Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis" TP-GAN is included in high school textbook and news[1][2][3]. [paper][arXiv][code]