Skip to content
View yiyexy's full-sized avatar
🎯
Focusing
🎯
Focusing
25 followers · 33 following
  • Shanghai,China

Achievements

Achievement: Pull Sharkx2Achievement: Pair ExtraordinaireAchievement: StarstruckAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx2Achievement: Pair ExtraordinaireAchievement: StarstruckAchievement: Quickdraw

Highlights

  • Pro

Block or report yiyexy

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
yiyexy/README.md

Hi there, I'm Yin Xie 👋 Email

🚀 About Me

I'm a Deep Learning Algorithm Engineer specializing in cutting-edge AI technologies. My passion lies in pushing the boundaries of computer vision and multimodal AI systems.

🔬 Research Interests

  • 🖼️ Computer Vision - Advanced visual understanding and perception
  • 🤖 Vision-Language Models - Large-scale multimodal AI systems
  • ⚡ Model Optimization - Compression, acceleration, and efficient deployment
  • 🌐 Distributed Training - Scalable deep learning infrastructure

💡 Current Focus

My recent work centers on:

  • Visual representation learning and self-supervised techniques
  • End-to-end facial feature pretraining systems
  • Advanced pretraining strategies for vision-language models
  • Publishing research in top-tier AI conferences
  • Contributing to impactful open-source projects

💬 Let's Connect!

I'm always open to:

  • 🤝 Collaborating on innovative AI projects
  • 💡 Discussing cutting-edge research ideas
  • 📚 Sharing knowledge and best practices
  • 🌟 Contributing to open-source initiatives

Feel free to reach out via email or connect with me here on GitHub!

Pinned Loading

  1. EvolvingLMMs-Lab/LLaVA-OneVision-2 EvolvingLMMs-Lab/LLaVA-OneVision-2 Public

    Fully Open Framework for Democratized Multimodal Training

    Python 1k 73

  2. EvolvingLMMs-Lab/OneVision-Encoder EvolvingLMMs-Lab/OneVision-Encoder Public

    Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

    Python 363 19

  3. EvolvingLMMs-Lab/lmms-eval EvolvingLMMs-Lab/lmms-eval Public

    One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

    Python 4.2k 597

  4. EvolvingLMMs-Lab/lmms-engine EvolvingLMMs-Lab/lmms-engine Public

    A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

    Python 783 35