Skip to content
View BolinLai's full-sized avatar

Block or report BolinLai

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
BolinLai/README.md

Hi there 👋

Welcome to my GitHub!

I am an Applied Scientist at Amazon AGI, working on LLM/VLM post-training (SFT+RL) and building real-time interactive models. Prior to that, I spent cumulative 2 years at Meta Superintelligence Labs working on foundation model research. I obtained my PhD from Georgia Tech and I am an associated scholar at UIUC.

My expertise and interests lie in LLM/VLM post-training, reasoning and agentic tool use. More details can be found in my homepage.

Please drop me an email if you have questions about my work or have interests in collaboration!

Pinned Loading

  1. SALT-NLP/PersuationGames SALT-NLP/PersuationGames Public

    [ACL2023] Source codes for the paper "Werewolf Among Us: Multimodal Resources for Modeling Persuasion Behaviors in Social Deduction Games"

    Python 16 5

  2. InstaManip InstaManip Public

    [CVPR 2025, Highlight] The official implementation of the paper "Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation"

    Jupyter Notebook 29 5

  3. LEGO LEGO Public

    [ECCV2024, Oral, Best Paper Finalist] This is the official implementation of the paper "LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning".

    Python 41

  4. FreqWarm FreqWarm Public

    [CVPR 2026] The official implementation of the paper "Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective"

    Python 3

  5. GLC GLC Public

    [BMVC2022, IJCV2023, Best Student Paper, Spotlight] Official codes for the paper "In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation".

    Python 36 10

  6. CSTS CSTS Public

    [ECCV2024] The official implementation of "Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation".

    Python 18 4