Scholar

Jialin Wu

Google Scholar ID: M7EpKqsAAAAJ

Google DeepMind

LMMparameter-efficient tuning

Citations & Impact

All-time

Citations

4,508

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

20 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

Selected Publications and Projects: Gemini 2.5 Flash Image (2025); Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025); Distilling vision-language models on millions of videos (2024); Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts (2024); CausalLM Is Not Optimal for In-Context Learning (2023).

Research Experience

Research Scientist: August 2022 – Present, Google Deepmind, Los Angeles; Research Intern: May 2020 – August 2020, Allen Institute for AI, Seattle; Research Intern: May 2019 – August 2019, Google Inc., New York City.

Education

PhD in Artificial Intelligence, 2017 - 2022, UT Austin, advised by Raymond J. Mooney; BEng in Automation, 2013 - 2017, Tsinghua University, supervised by Prof. Xiangyang Ji.

Background

Research Interests: Info-seeking Image Generation, Scaling Laws for Image Generation. Biography: Currently a research scientist at Google Deepmind, focusing on enhancing the capabilities of image generation models on info-seeking (world knowledge) queries.

Co-authors

15 total