Bolin Lai

Hi! I am a 5th-year PhD student in the Machine Learning Program of Georgia Institute of Technology, advised by Prof. James Rehg and co-advised by Prof. Zsolt Kira. Currently, I'm also a visiting student at CS department of UIUC. Prior to my PhD, I got my Master's degree majoring in ECE and Bachelor's degree majoring in Information Engineering from Shanghai Jiao Tong University. I worked with Prof. Ya Zhang during my master.

I interned at Meta GenAI (now Meta Superintelligence Labs) for three times working on research of generative models. My projects span multimodal LLMs, image/video diffusion models, autoregressive architectures and fundamental research on tokenizers. Please check my employment experiences and publications below for details.

Email  /  Google Scholar  /  Github  /  LinkedIn  /  Twitter

I'm looking for a full-time Research Scientist / Applied Scientist / ML Engineer position (available starting Dec. 2025). Please drop me an email if you think I'm a good fit in your team.

Research Interests

My research interests lie in Multimodal Learning, including Multimodal Understanding (e.g., VLMs, MLLMs) and Image/Video Generation (e.g., diffusion, flow matching). My career goal is to build omni multimodal systems that can understand, reason, and generate across text, image, video, and audio -- by integrating LLM planning/reasoning agents and high-fidelity diffusion backends into one autoregressive architecture.

I'm always looking for self-motivated graduate/ungraduate students to collaborate with. Don't hesitate to reach out to me if you are interested in my research.

News

Employment

• [May 2025 – Present] Research Scientist Intern
  Meta Superintelligence Labs, Multimedia Core Video Generation Team
  
  • Analyzing and improving the diffusibility of high-dimension latent space for image/video generation (In Progress).     [Role: project leader, first author]
  • Engineering experience on large-scale MovieGen codebase and distributed training.
  • Mentor & Manager: Ishan Misra
  • Collaborators: Xudong Wang, Rohit Girdhar, Saketh Rambhatla


• [May 2024 – Dec. 2024] Research Scientist Intern
  Meta GenAI, Llama Applied Multimodal Team
  
  • Omni autoregressive architecture for unified multimodal understanding and generation (CVPR 2025, Highlight).     [Role: project leader, first author]
  • Proposed novel group self-attention mechanism to improve reasoning capabilities of LLMs on multimodal tasks.
  • Mentor: Tong Xiao      Manager: Ning Zhang
  • Collaborators: Felix Juefei-Xu, Miao Liu, Xiaoliang Dai, Nikhil Mehta, Chenguang Zhu


• [May 2023 – Dec. 2023] Research Scientist Intern
  Meta GenAI, Llama Image/Video Data Team
  
  • LLM-enhanced instructional image generation in the real-world environment (ECCV 2024, Oral, Best Paper Finalist).     [Role: project leader, first author]
  • Proposed to bridge feature spaces of LLMs and diffusion models by learnable layers for complex action generation.
  • Mentor: Miao Liu      Manager: Guan Pang
  • Collaborators: Xiaoliang Dai, Lawrence Chen

Publications

Awards and Service

• EgoVis Distinghuished Paper Award @CVPR2025
• CVPR Outstanding Reviewer (2025)
• ECCV Best Paper Finalist (2024)
• BMVC Best Student Paper Prize (2022)
• Outstanding Graduate of SJTU (2020)
• Taught ECE4871 as a teaching assistant at Georgia Tech in 2021 and 2022.
• Taught CS7643 Deep Learning as a teaching assistant at Georgia Tech in 2024 and 2025.

• Computer Vision and Pattern Recognition Conference (CVPR)
• International Conference on Computer Vision (ICCV)
• European Conference on Computer Vision (ECCV)
• Conference on Neural Information Processing Systems (NeurIPS)
• The Association for Computational Linguistics (ACL)
• Empirical Methods in Natural Language Processing (EMNLP)
• Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
• International Journal of Computer Vision (IJCV)
• Association for the Advancement of Artificial Intelligence (AAAI)
• International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)
• ACM Multimedia (ACM MM)
• Journal of Biomedical and Health Informatics (JBHI)
• IEEE Signal Processing Letters (SPL)

This website is adapted from this source code.