HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Wed, 17 Dec 2025 18:19:32 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"6942f434-dd2" expires: Sun, 28 Dec 2025 09:35:42 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 0A2E:2DDCFF:771D81:857F1C:6950F796 accept-ranges: bytes age: 0 date: Sun, 28 Dec 2025 09:25:42 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210066-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766913943.541997,VS0,VE208 vary: Accept-Encoding x-fastly-request-id: 4092701ff7f4921279cb7ded9e635ec0ca388b1f content-length: 1258

Cheng Luo

I am a researcher focusing on LLM optimization. Before that, I was an research at Microsoft Research. I am also collaborating with Anima Anandkumar. at Caltech, Beidi Chen at CMU. I am currently a researcher at TikTok

I am interested in bridging hardware constraints with the principles of LLM. I focus on developing efficient reasoning, training and inference. Check out my research for more details.

Additionally, I am a passionate community builder, which I founded the Efficient Reasoning workshops.