Skip to content
View Tacossp's full-sized avatar

Highlights

  • Pro

Block or report Tacossp

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
Tacossp/README.md

Hi there πŸ‘‹, I'm Youping Gu!

My research interests lie at the intersection of Multimodal Large Models, Generative Models, and Efficient AI.

🌟 About Me

  • 🏫 I'm an undergraduate student at Xidian University, majoring in Data Science within the School of Computer Science and Technology.
  • πŸ”­ I'm passionate about Deep Learning, Computer Vision, and especially interested in efficient video generation and multimodal reasoning.
  • πŸš€ I am currently an intern at DAMO Academy (Alibaba Group), and concurrently at ZIP Lab.

πŸ“ Publications

  • [ICLR 2026] BLADE: A Joint Framework of Sparse Attention and Step Distillation for Efficient Video Generation
  • [ICML 2026] World-R1: World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

πŸ“ Preprints

  • PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation

πŸ“Š GitHub Stats

Tacossp's GitHub stats

πŸ› οΈ Tech Stack

Here are some of the technologies I am proficient with:

Python PyTorch Triton

🌐 Find me around the web

Platform Link Description
πŸ’» GitHub github.com/Tacossp My projects and code
πŸ“§ Email youpgu71@gmail.com Feel free to reach out

Pinned Loading

  1. ziplab/BLADE ziplab/BLADE Public

    [ICLR 2026] This is the official PyTorch implementation of "BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation."

    Python 42 5

  2. World-R1 World-R1 Public

    Forked from microsoft/World-R1

    [ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

    Python