Manli Shu
Scholar

Manli Shu

Google Scholar ID: WPYkxjgAAAAJ
Google DeepMind
Multimodal modelsLarge language models
Citations & Impact
All-time
Citations
1,687
 
H-index
16
 
i10-index
20
 
Publications
20
 
Co-authors
11
list available
Resume (English only)
Academic Achievements
  • Published multiple papers, including 'xGen-MM (BLIP-3): A Family of Open Large Multimodal Models,' and presented or showcased work at various international conferences such as ICRA'24, NeurIPS, etc.
Research Experience
  • Interned at Nvidia, Salesforce, and Google during her years at UMD; joined Salesforce Research in 2024; became a research scientist at Google Deepmind in 2025.
Education
  • Graduated from the University of Science and Technology of China (USTC) in 2019; obtained a Ph.D. in Computer Science from the University of Maryland, College Park (UMD) in 2024, advised by Tom Goldstein.
Background
  • A research scientist at Google Deepmind, focusing on Gemini multimodal understanding. Her research interests include the safety and trustworthiness of AI/ML in both vision and language modalities.
Miscellany
  • Always excited to explore new ideas and collaboration opportunities, feel free to reach out.