Recent content on Yue Wu
This article is aimed at those who want to do post-training alignment of generative models, but aren’t sure where to start. I give a end-to-end example of using human feedback data to align a generative model with direct preference optimization (DPO). I cover these steps:
This article is aimed at those who want to understand exactly how diffusion models work, with no prior knowledge expected. I’ve tried to use illustrations wherever possible to provide visual intuitions on each part of these models. I’ve kept mathematical notation and equations to a minimum, and where they are necessary I’ve tried to define and explain them as they occur. Intro…
For associated code, please see the github repo . Huge shoutout to my old friend Daniel Tse , linguist and ML expert extraordinaire for invaluable help and ideas on both fronts throughout this campaign.
For associated code, please see the Jupyter notebook in the github repository While machine learning has been very successful in image-processing applications, there’s still a place for traditional computer vision techniques. One of my hobbies is making timelapse videos by taking photos every 10 minutes for many days, weeks or even months. Over this time scale, environmental effects such as…
Generative text-to-image models have recent become very popular. Having a bunch of fully captioned images left over from the This JACS Does Not Exist project, I’ve trained a Stable Diffusion checkpoint on that dataset (~60K JACS table-of-contents images with matched paper titles). It seems to work pretty well. Here are some examples of prompts and the resulting images generated:…
For the language-to-language components of this JACS does not exist , I chose Google’s T5 (text-to-text transfer transformer) as a recent cutting-edge text sequence to sequence model. I had already scraped all the JACS titles and abstracts, so training data was readily available. The first task was to generate somewhat-convincing abstracts from titles to increase the entertainment value of…
Many people enjoyed title2abstract from the this JACS does not exist project so I inverted the training parameters for a quick follow up. Presenting abstract2title: You can also test the title2abstract and toc2title apps in my previous post.
Broadly: materials science, applications of machine learning, autonomous experimentation Projects I’ve worked on previously: A new method for intelligent exploration of design spaces beyond Bayesian optimization. With Bayesian algorithm execution (BAX), any design space exploration question can easily be optimized, e.g.: “find synthesis conditions for nanoparticles with dispersity <5%…
Research Associate, SSRL , SLAC , Stanford. 2022-2023 Research Lead, Cooper group , Materials Innovation Factory , University of Liverpool. 2019-2021 Postdoc, Cheetham & Wang groups, National University of Singapore. 2017-2019 Postdoc, Cheetham group, University of Cambridge. 2016-2017 Postdoc, O’Hare group, University of Oxford. 2014-2016 PhD (Chemistry), Kepert group, University of Sydney.…
An imaginary abstract generated at thisJACSdoesnotexist.com In academic chemistry, authors submit a promotional table-of-contents (ToC) image when publishing research papers in most journals. These fascinate me as they are one of the few places where unfettered self expression is tolerated, if not condoned. (See e.g. TOC ROFL , of which I am a multiple inductee ) In general, though, ToC images…
I enjoy taking care of plants and making time-lapse videos of their growth - lots of examples on my youtube channel . I sometimes design and 3D print things. I used to be an avid archer and martial artist.