Skip to content
View qianqiaoai's full-sized avatar
🎯
Focusing
🎯
Focusing
4 followers · 1 following

Achievements

Achievement: Quickdraw

Achievements

Achievement: Quickdraw

Block or report qianqiaoai

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
qianqiaoai/README.md

Hi there, I'm Qian Qiao! 👋

Typing SVG

Homepage OpenReview Profile Views Google Scholar

🚀 About Me

👨‍💻 Professional Profile

🎯 Role: Algorithm Researcher @ Soul AILab
🎓 Education: M.S. Computer Science
📌 Focus: AIGC, Embodied Intelligence, Multimodal LLMs

🔬 Specialization

  • 🤖 Multimodal Large Models & Diffusion Language Models
  • 🎬 Video Generation & Text Editing
  • 🗣️ Digital Humans (Real-time, Interactive & Audio-driven)
  • 🌍 Embodied Intelligence (VLA / World Models)

🎯 Current Focus

  • 🌐 World Models & Sequence Modeling
  • 👤 Real-time Streaming Digital Humans
  • 📝 Diffusion Language Models

💡 Interests

  • 🔬 AI Research
  • 🌟 Open Source
  • 💻 Travel

💭 Thanks for reaching out! Looking forward to building something great together!

🛠️ Tech Stack

🎯 Model Expertise

Frameworks & Architectures

  • 🐍 Python, PyTorch
  • 🧠 Transformer & Diffusion Architectures
  • 👁️ Multimodal (Vision-Language) Learning
  • 📝 Diffusion Language Models

Domains & Systems

  • 🤖 Embodied AI (Vision-Language-Action)
  • 🌐 World Models
  • 🗣️ Audio-driven Generation Systems
  • ⚡ Real-time Inference & Interactive Streaming

📊 GitHub Stats

GitHub Streak

🎯 What I'm Up To

👨‍💻 Currently Working On

projects:
  - Real-time Audio-driven Digital Humans (Core Contributor to SoulX-FlashTalk & SoulX-FlashHead)
  - Multimodal Large Models
  - Video Generation & Text Editing

🌱 Currently Learning

learning:
  - World Models
  - Real-time Interaction
  - Diffusion Language Models

🤝 Let's Collaborate!

I'm always excited to collaborate on:

  • 🔬 Research Projects - Pushing the boundaries of AIGC & Embodied AI

  • 🌟 Open Source - Contributing to impactful Multimodal/Video models

  • 💡 Generative AI - Building next-gen real-time interactive tools

  • 🎓 Knowledge Sharing - Writing, teaching, and learning together

📫 Connect With Me

Email WeChat

✨ Thanks for visiting! ✨

Pinned Loading

  1. Soul-AILab/SoulX-FlashTalk Soul-AILab/SoulX-FlashTalk Public

    SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.

    Python 1.5k 138

  2. Soul-AILab/Soul-AILab.github.io Soul-AILab/Soul-AILab.github.io Public

    JavaScript 17 5

  3. Soul-AILab/SoulX-FlashHead Soul-AILab/SoulX-FlashHead Public

    SoulX-FlashHead: A unified 1.3B-parameter framework designed for high-fidelity, infinite-length, and real-time streaming portrait video generation.

    Python 999 117

  4. qianweijiujiu/Awesome-Token-Pruning-and-Merging-for-Multimodal-Large-Language-Models qianweijiujiu/Awesome-Token-Pruning-and-Merging-for-Multimodal-Large-Language-Models Public

    papers for token compression in mllms.

    8