Efficient LLM inference
Lightweight large-language-model algorithms and hardware design for low-latency on-device inference.
Contact Jiawen QiWe welcome motivated students and researchers interested in efficient intelligent systems.
Project scope is shaped around your background and interests. The themes below are available on an ongoing basis.
Lightweight large-language-model algorithms and hardware design for low-latency on-device inference.
Contact Jiawen QiEEG foundation models and efficient physiological signal processing for healthcare.
Contact Guorui LuEvent-camera algorithms and embedded systems for extended reality and robotics.
Contact Zhen XuHardware–software co-design for compact audio language models and FPGA deployment.
Contact Jiayu LiuInterested scholars and students are welcome to contact us about research visits, exchange projects, and collaboration.
Contact the group