About Me

I am a Machine Learning Engineer at EmbodyX Inc. & AIbao LLC. I started with real-time AI systems, building TTS-integrated chatting avatars and streaming pipelines. From there, I moved into MoE large model compression — pruning, quantization, and edge deployment. Recently, I have been exploring MoE efficient decoding and picking up vibe coding along the way. I am also a passionate open-source enthusiast and enjoy contributing to the community whenever I can.

Previously, I worked as a Software Engineering Co-op at Cognex Corporation, where I developed .NET wrapper layers and contributed to VisionPro software.

I received my M.S. in Electrical and Computer Engineering from Northeastern University and my B.E. in Electrical Engineering from Beijing University of Technology.

Research Interests

• MoE Efficient Decoding & LLM Compression
• Edge Computing & On-device AI Inference
• Computer Vision & Autonomous Driving Perception