Sign in

Danilo J. Rezende

@danilojrezende.bsky.social
1.6K followers 331 following 20 posts

VP of AI Research, Principal Scientist @ EIT Oxford | ex-Director @ DeepMind Building models to accelerate fundamental sciences and medicine. Opinions my own. danilorezende.com

PostsRepliesMedia
Danilo J. Rezende @danilojrezende.bsky.social · 16/01/2025
Amazing, congrats!
120
Danilo J. Rezende @danilojrezende.bsky.social · 27/12/2024
Indeed, additionally If computing the forces in HMC is computationally cheap - it's extremely hard to beat it with learnt samplers in terms of wall clock time. Similar challenge to Neural PDE solvers.
040
Reposted by Danilo J. Rezende
Guillem Simeon @guillemsimeon.bsky.social · 25/12/2024
Happy Newton’s birthday to those who celebrate
1111
Danilo J. Rezende @danilojrezende.bsky.social · 24/12/2024
Should cite Newton first 😂
110
Reposted by Danilo J. Rezende
Sander Dieleman @sedielem.bsky.social · 02/12/2024
In arxiv.org/abs/2303.00848, @dpkingma.bsky.social and @ruiqigao.bsky.social had suggested that noise augmentation could be used to make other likelihood-based models optimise perceptually weighted losses, like diffusion models do. So cool to see this working well in practice!
arxiv.org
Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation
To achieve the highest perceptual quality, state-of-the-art diffusion models are optimized with objectives that typically look very different from the maximum likelihood and the Evidence Lower Bound (...
05311
Danilo J. Rezende @danilojrezende.bsky.social · 21/12/2024
Very nice results!
100
Reposted by Danilo J. Rezende
Andrew Gordon Wilson @andrewgwils.bsky.social · 18/12/2024
This is your monthly reminder that understanding deep learning does not require rethinking generalization, and it never did.
3223
Reposted by Danilo J. Rezende
Dhruv Batra @dhruvbatra.bsky.social · 14/12/2024
Brilliant talk by Ilya, but he's wrong on one point. We are NOT running out of data. We are running out of human-written text. We have more videos than we know what to do with. We just haven't solved pre-training in vision. Just go out and sense the world. Data is easy.
59916
Danilo J. Rezende @danilojrezende.bsky.social · 12/12/2024
Hi!
010
Danilo J. Rezende @danilojrezende.bsky.social · 09/12/2024
Neat!
010
Danilo J. Rezende @danilojrezende.bsky.social · 07/12/2024
More a linear algebra meme than a QM meme 😅
141
Reposted by Danilo J. Rezende
Frank Noe @franknoe.bsky.social · 06/12/2024
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science. www.biorxiv.org/content/10.1...
21441147
Danilo J. Rezende @danilojrezende.bsky.social · 07/12/2024
Amazing work!
120
Danilo J. Rezende @danilojrezende.bsky.social · 04/12/2024
Just use github
010
Reposted by Danilo J. Rezende
Kyle Cranmer @kylecranmer.bsky.social · 02/12/2024
My former student @msalbergo.bsky.social has beautiful papers describing the approach on the right. “Flow matching” and “stochastic interpolants” were concurrent developments of the same core idea. arxiv.org/abs/2209.15571 arxiv.org/abs/2303.08797
2404
Reposted by Danilo J. Rezende
Miles Cranmer @milescranmer.bsky.social · 02/12/2024
🧵 Today with @polymathicai.bsky.social and others we're releasing two massive datasets that span dozens of fields - from bacterial growth to supernova! We want this to enable multi-disciplinary foundation model research.
38825
Danilo J. Rezende @danilojrezende.bsky.social · 30/11/2024
As a statistical inequality hoarder, I approve 😅
030
Reposted by Danilo J. Rezende
Guillaume Dalle @gdalle.bsky.social · 30/11/2024
A paper a day, episode 15. You liked the matrix cookbook? You’re gonna love this one. 100 statistics inequalities just for your personal enjoyment. As they say in French, moi j’ai Bienaymé cet article ! arxiv.org/abs/2102.07234
arxiv.org
One Hundred Probability and Statistics Inequalities
Herein we present one hundred inequalities culled from various corners of the probability, statistics, and combinatorics literature. We welcome new suggestions.
55910
Danilo J. Rezende @danilojrezende.bsky.social · 30/11/2024
What do you mean by physical? Eg If the target density lives on a specific manifold, RFs will generally not respect that naively (eg think of data living on a torus). One would have to choose paths along geodesics for example and then properly integrate the flow on the manifold.
120
Danilo J. Rezende @danilojrezende.bsky.social · 30/11/2024
Yes, though a simplification is that the log-det-jac is the integral of the divergence. So "just" need to solve a 1d integral.
010
Danilo J. Rezende @danilojrezende.bsky.social · 30/11/2024
You can, just need to integrate it's divergence to get the likelihood.
010
Danilo J. Rezende @danilojrezende.bsky.social · 29/11/2024
What do you mean? That's the whole field of optimisation (preconditioning, proximal, natural, etc...)
040
Danilo J. Rezende @danilojrezende.bsky.social · 27/11/2024
🥹
040
Danilo J. Rezende @danilojrezende.bsky.social · 27/11/2024
I have quite a few of those 😅
110
Reposted by Danilo J. Rezende
Guillaume Dalle @gdalle.bsky.social · 26/11/2024
For the theoretical side, there’s no better resource than the 2024 book by Blondel and Roulet: arxiv.org/abs/2403.14606 For the practical side, my friend @willtebbutt.bsky.social wrote stellar documentation explaining autodiff with mutation: compintell.github.io/Mooncake.jl/...
arxiv.org
The Elements of Differentiable Programming
Artificial intelligence has recently experienced remarkable advances, fueled by large models, vast datasets, accelerated hardware, and, last but not least, the transformative power of differentiable p...
55612
Danilo J. Rezende @danilojrezende.bsky.social · 25/11/2024
Not sure it works well here neither. Still seeing lots of cartoons and cat pictures instead of papers.
210
Reposted by Danilo J. Rezende
Simon Batzner @simonbatzner.bsky.social · 25/11/2024
We're hiring! Our team at Google DeepMind is looking for a research engineer to join us. More details in the link below. boards.greenhouse.io/deepmind/job...
boards.greenhouse.io
Research Engineer, Materials Science
London, UK
0346
Danilo J. Rezende @danilojrezende.bsky.social · 25/11/2024
🤔
120
Danilo J. Rezende @danilojrezende.bsky.social · 25/11/2024
A cargo train would probably be the most efficient by far?
000
Reposted by Danilo J. Rezende
Surya Ganguli @suryaganguli.bsky.social · 25/11/2024
This video takes pedagogy to a whole new level in teaching the Schrödinger equation! youtu.be/uVKMY-WTrVo?...
youtu.be
What is the i really doing in Schrödinger's equation?
YouTube video by Welch Labs
47713
Danilo J. Rezende @danilojrezende.bsky.social · 21/11/2024
Nice!
010
Reposted by Danilo J. Rezende
Jennifer Johnson @jajohnson.bsky.social · 18/11/2024
Updated periodic table with origin of elements in the Solar System (for boron and lithium at least)
periodic table of the elements color-coded by origin in the solar system. Learning more at this conference about how much of orange should be turned green
45950294