William Luo
Phd on Statistics in PKU Research Interests: Generative AI and Large Language Models.
This profile was put together from William's public GitHub portfolio, and they haven't joined Vibetown yet, so reach them through their portfolio. Is this you? Contact us to update or remove it.
About
William Luo works in AI engineering and ML & data science, based in Beijing (Peking University). Phd on Statistics in PKU Research Interests: Generative AI and Large Language Models. Public projects on GitHub include Diff Instruct (official code for Diff-Instruct algorithm for one-step diffusion distillation), Easy Meanflow (A clean Pytorch Implementation of Mean Flow, with FID evaluation on the fly) and DeepCtr (DeepCtr deep recommendation with transformer), mostly written in Python, Jupyter and HTML.
Projects 6
Diff Instruct
official code for Diff-Instruct algorithm for one-step diffusion distillation
github.comEasy Meanflow
A clean Pytorch Implementation of Mean Flow, with FID evaluation on the fly
github.comDeepCtr
DeepCtr deep recommendation with transformer
github.com- github.com
Diff Instruct Star
We introduce DI*-SDX-1step Model, which is a leading human-preferred 1-step text-to-image model of 1024 resolution.
Diff Instruct Pp
We introduce Diff-Instruct++, a novel approach for human preference alignment of 1-step text-to-image generation.
github.com- github.com
Sd3 Inference
Inference code for SD3