Ying Li
👋 Hi, I’m Ying Li, a researcher focusing on Efficient AI, Large/Multimodal Language Model (LLM/MLLM) Inference, and Machine Learning Systems (MLSys).
My work aims to make large models more efficient, adaptive, and deployable on resource-constrained platforms — spanning areas from dynamic inference to AI for Science.
I am currently based in Hangzhou, Zhejiang, China, and affiliated with Westlake University.
Research Interests
- Efficient AI & model compression
- LLM/MLLM inference acceleration
- Dynamic and speculative decoding
- Machine learning systems & optimization
- AI for Science
Links