Skip to content
View drewjin's full-sized avatar

Highlights

  • Pro

Block or report drewjin

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
drewjin/README.md

πŸ’­ About Me

πŸ‘‹ Hi, I’m @drewjin (Yijie Jin), an Incoming Ph.D. Student of DENG Lab @ SJTU, and a Research Intern @ Qwen.

🎯 Focus

πŸ”¬ I conduct in-depth research at the intersection of Machine Learning Systems and Efficient Generative AI, with a focus on Algorithm-System Co-Design. Specifically, I'm interested in:

  • Diffusion Language Models: modeling, acceleration, and the corresponding inference infrastructure (checkout Diffulex)
  • Efficient Interactive World Models: exploring algo-sys co-optimizations for real-time efficiency of interactive world simulation

πŸš€ Skills

😊 Contact Me

  • E-mail: drewjin0827@gmail.com

  • Visit my Zhihu Drew!

Pinned Loading

  1. SJTU-DENG-Lab/Diffulex SJTU-DENG-Lab/Diffulex Public

    Flexible and Pluggable Serving Engine for Diffusion LLMs

    Python 144 19

  2. SJTU-DENG-Lab/mbd-lms SJTU-DENG-Lab/mbd-lms Public

    Multi-Block Diffusion Language Models

    Python 25

  3. SJTU-DENG-Lab/Discrete-Diffusion-Forcing SJTU-DENG-Lab/Discrete-Diffusion-Forcing Public

    Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference

    Python 258 18

  4. SJTU-DENG-Lab/LoPA SJTU-DENG-Lab/LoPA Public

    LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding

    Python 39 2

  5. GsiT GsiT Public

    [ACL 2025 (Main)] Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs

    Jupyter Notebook 10

  6. sglang sglang Public

    Forked from sgl-project/sglang

    SGLang is a fast serving framework for large language models and vision language models.

    Python