Enough games. The RL field needs to mature. New blog post with shiemannor avivtamar.substack.com/p/deployablerl…

Human bilinguals are more robust to dementia and cognitive decline. In our recent NeurIPS paper we show that bilingual GPT models are also more robust to structural damage in their neuron weights. Further, we develop a theory.. (1/n)

This was already a great monograph! I've enjoyed using it for my class. Looking forward to checking out the updated version.

A tractable 2nd order correction to standard Tweedie's application to diffusions. Seems to make a significant impact in performance. Work with Litu Rout and colleagues at Google and UT Austin.

Excited to be the director for the new Texas Center for Generative AI

Super excited about this transformative center!

Today, with collaborators at Google and UT Austin, we're announcing 🤖 RB-Modulation 🤖! It's a whole new training-free framework for conditioning on reference images (for style or subject) without adapters (!) with an elegant formulation 🔥 web: rb-modulation.github.io

I was thrilled to learn about this best paper award announced today in COLT 2024, the premier learning theory venue. The paper is "Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension" authored by students Gautam Chandrasekaran, Konstantinos Stavropoulos, IFML

Thanks Sylvain Filoni for making the demo of our paper RB-Modulation 🎯 🚀 GitHub Code: github.com/google/RB-Modu… 🌐 Project Page: rb-modulation.github.io 📰 Paper: arxiv.org/pdf/2405.17401

Try out web-demo of our project RB-Modulation: 🔥 huggingface.co/spaces/fffilon… Prompts: "Albus Dumbledore" | "Harry Potter" | "Hermione Granger" | "Ron Weasley"

RB-Modulation demo is number one Space of the Week Hugging Face 👏 Thanks to Litu Rout Nataniel Ruiz Linoy Tsaban🎗️ and apolinario 🌐 for their trust on this project 🙏 —> Explore this week selection: hf.co/spaces 🤗

No IP-Adapters, no LoRAs, no ControlNets required. Try RB-Modulation🎁, a training-free personalization framework! 🔥 Web-demo: huggingface.co/spaces/fffilon… 🚀 GitHub Code: github.com/google/RB-Modu… 🎯 Project Page: rb-modulation.github.io 📰 ArXiv Preprint: arxiv.org/pdf/2405.17401

Today, I'm excited to share something we've been working at Google. We present the first effective inversion and semantic editing method for rectified flow models like Flux. Think SDEdit but for the new generation of models. Results are truly beautiful. Link in next tweet 🧵 1/N

Harvard has set an example for other higher-ed institutions – rejecting an unlawful and ham-handed attempt to stifle academic freedom, while taking concrete steps to make sure all students at Harvard can benefit from an environment of intellectual inquiry, rigorous debate and