Jialin Wu

Jialin Wu

Research Scientist

Google Deepmind

Biography

I am a research scientist at Google Deepmind. Prior to that, I received my Ph. D. from UTCS advised by Raymond J. Mooney. I received my BEng. degree from the Department of Automation supervised by Prof. Xiangyang Ji at Tsinghua University in 2017.

My most recent research interests is building large multimodal models that (1) are explainable generalists and (2) performan well on geographically (culturally) diversed tasks. I am also interested in few-shot learning, parameter efficient learning and continual learning.

Interests
  • Fewshot (In-Context) Learning
  • Language and Vision
  • Explainable AI
Education
  • PhD in Artificial Intelligence, 2017 - 2022

    UT Austin

  • BEng in Automation, 2013 - 2017

    Tsinghua University

Selected Publications

Please see my google scholar for full publications and preprints.
(2024). Distilling vision-language models on millions of videos. CVPR 2024.

PDF

(2024). Omni-SMoLA:Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts. CVPR 2024 (Highlight Poster).

PDF

(2023). CausalLM Is Not Optimal for In-Context Learning. ICLR 2024.

PDF

(2023). PaLI-X:On Scaling up a Multilingual Vision and Language Model. CVPR 2024.

PDF

(2023). RT-2:Vision-language-action models transfer web knowledge to robotic controling. CoRL 2023.

PDF

Experience

 
 
 
 
 
Research Scientist
August 2022 – Present Los Angelos
 
 
 
 
 
Research Intern
May 2020 – August 2020 Seattle
 
 
 
 
 
Research Intern
May 2019 – August 2019 New York City