We built a new diffusion protein design model named Genie. We preprinted it a while ago (soon after RFDiffusion and Chroma preprints) but kept mum due to embargo. Final ICML version (major update) with code github.com/aqlaboratory/g… and paper here arxiv.org/abs/2301.12485 (1/7)

The fact that there are multiple candidates for what this linear regression is blows my mind 🤯 (Original, of course: xkcd.com/2347/)

R² is a widely used measure of fit, but for many analysts, it is just a number. They believe high R² ➡ Good predictions. This is not always true! Now I will clarify. 🔽 R-squared

Yesterday, I gave a technical presentation to Luca Ambrogioni’s group on Blackout Diffusion (lnkd.in/e6Ze4dq9). The group was so kind to record the talk and share with netizens ⬇️ Special thanks to Gianluigi Silvestri for organizing the presentation!

Our paper "Spontaneous symmetry breaking in generative diffusion models" was accepted at NeurIPS Conference 2023! We found that the generative capabilities of diffusion models are the result of a phase transition! Preprint: arxiv.org/abs/2305.19693 Code: github.com/gabrielraya/sy…

Who else is countering the LLM "AGI" narrative? Google product manager for Bard! (From bloomberg.com/news/articles/… by Davey Alba) 👀 ⬇️

Our Blackout paper (ICML 23) made LANL front page! Zach Fox Javier E. Santos Los Alamos National Laboratory discover.lanl.gov/news/0111-ai-b…

Eyes on her feet... the so-called "AI".

Liouville Flow Importance Sampler (LFIS), an innovative flow-based sampler that achieved state-of-the-art performance over a range of test problems. arxiv.org/abs/2405.06672 YIFENG TIAN #ICML2024

Yes, I've made this point many times. The beginning of a sigmoid looks like an exponential. Not only can we "never be fully certain that what we are observing isn't in fact following a logistic trend before the inflection point", we can always be fully certain that *every*

The question of whether LLMs can reason is, in many ways, the wrong question. The more interesting question is whether they are limited to memorization / interpolative retrieval, or whether they can adapt to novelty beyond what they know. (They can't, at least until you start

9.11 is still larger than 9.8, despite can memorize solutions to PhD level questions. Again, memorizing is not understanding and knowledge is not intelligence.