The Future of AI is Compact
Scaling Intelligence, Cutting Cost.
Our research group is dedicated to pioneering techniques—from sparse efficient architectures to scalable inference paradigms—that make large language models accessible and deployable on commodity hardware.
Research Areas
We focus on the intersection of theoretical efficiency and practical deployment.
Recent Publications
See our latest breakthroughs in model compression and inference.
Drive the Next Wave of Efficient AI.
We are always looking for passionate researchers, engineers, and PhD students. Join our highly collaborative environment.