Skip to content
View sunrainyg's full-sized avatar
🐯
🐯
179 followers · 19 following

Achievements

Achievement: Starstruckx3Achievement: Pull Shark

Achievements

Achievement: Starstruckx3Achievement: Pull Shark

Highlights

  • Pro

Organizations

@AlaaLab

Block or report sunrainyg

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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
sunrainyg/README.md

Yulu Gan Google Scholar LinkedIn Twitter

Bio

Hi there, I am Yulu Gan, a PhD student at CSAIL, MIT.

Previously, I graduated from Peking University in July 2024. In 2023, I was a visiting student at CBMM, MIT, studying ML theory, and also conducted several months of remote research at EECS, UC Berkeley.

Research interests

I am interested in multimodalities and exploring the emergence of intelligence.

Interests Beyond Research

Swimming, Basketball, Badminton, Reading, Saxophone

Blogs

Some of my early blogs on ML, CV, and RL.

Recent talks:

How to build Vision Generalists - the presentation for the ICLR paper InstructCV.

Visual Prompting for Continual Test Time Adaptation - the presentation for the AAAI Outstanding Student Paper VDP.

Project pages:

Here are some websites where my papers have been featured.

Pinned Loading

  1. AlaaLab/InstructCV AlaaLab/InstructCV Public

    [ ICLR 2024 ] Official Codebase for "InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists"

    Python 459 39

  2. VsonicV/es-fine-tuning-paper VsonicV/es-fine-tuning-paper Public

    This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"

    Python 354 38

  3. Wolfv0/FoundationMotion Wolfv0/FoundationMotion Public

    Python 133 2

  4. RandOpt RandOpt Public

    Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)

    Python 587 61

  5. verl-project/verl verl-project/verl Public

    verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

    Python 21.2k 3.8k

  6. verl-project/verl-recipe verl-project/verl-recipe Public

    A set of examples based on verl for end-to-end RL training recipes.

    Python 264 112