About

Introduction

Jiang Yi (姜祎) is an AI software engineer, where he focuses on pushing the boundaries of artificial intelligence through cutting-edge research in Multimodal Large Language Models (MLLMs) and Vision Language Action (VLA). He also goes by the name “温故知新” on platforms such as Zhihu, Bilibili, and WeChat Official Account.


Research Interests

My research focuses on the intersection of language and vision, with particular emphasis on:

  • Large Language Models (LLMs) - Advancing the capabilities of language understanding and generation
  • Multimodal Large Language Models (MLLMs) - Bridging vision and language for unified AI systems
  • Reasoning Models - Developing systems capable of complex logical reasoning
  • Unified Understanding & Generation - Creating models that seamlessly integrate comprehension and creation

Academic Background


Get in Touch

I’m always excited to discuss research collaborations, innovative ideas, or potential opportunities. Feel free to reach out!

Email: jxyevil@163.com

Resume/CV: Download PDF


Find Me Online


About This Blog

This blog serves as my digital garden where I share insights, research notes, and explorations in the field of artificial intelligence. Here you’ll find:

  • Technical Deep Dives - In-depth analyses of recent papers and models
  • Research Notes - Thoughts and observations from my research journey
  • Practical Guides - Tutorials and implementation details
  • Reflections - Perspectives on AI trends and future directions

I occasionally create educational content on Bilibili to make complex AI concepts more accessible. Feel free to check it out and share your thoughts!

Licensed under CC BY-NC-SA 4.0
Last updated on April 9, 2026 at 2:56 PM
Built with Hugo
Theme Stack designed by Jimmy