Scholar

Di Liu

Google Scholar ID: 1uo3XsMAAAAJ

Research Scientist, Meta Reality Labs

Computer VisionVision-language ModelsComputer GraphicsMedical Image Analysis

Citations & Impact

All-time

Citations

761

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

20 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Research Experience

Jul. 2025 – Present: AI Research Scientist at Meta Reality Labs (Seattle), working on foundational Generative AI research including World Models, 3D/4D Generation, Character Animation, and Multi-modality Perception.
May 2025 – Jul. 2025: Applied Scientist Intern at Amazon Fashion, focusing on Multi-modal LLMs and Diffusion Models for personalized recommendation and stylized content generation.
Jan 2025 – May 2025: Research Scientist Intern at Snap Research (New York), working on instant generation of animatable dual-stylized avatars.
May 2024 – Nov. 2024: Research Scientist Intern at Meta Reality Labs Research (Pittsburgh), developing universal layered codec avatar reconstruction from videos (published at CVPR'25).
Jan. 2024 – May 2024: Research Scientist Intern at Microsoft (Redmond), working on large-scale multi-modality pretraining and vision-language models.
Jun. 2023 – Dec. 2023: Research Intern at NEC Labs America (San Jose), researching instantaneous 3D perception of moving objects (published at CVPR'24).
Sept. 2021 – Jun. 2025: Graduate Assistant at Rutgers University under Prof. Dimitris N. Metaxas, working on Large Sign Language Models for 3D ASL translation, text-to-character blendshape generation, and more.

Co-authors

16 total