Danilo J. Rezende
@danilojrezende.bsky.social
VP of AI Research, Principal Scientist @ EIT Oxford | ex-Director @ DeepMind Building models to accelerate fundamental sciences and medicine.
Opinions my own.
https://danilorezende.com/
Opinions my own.
https://danilorezende.com/
Reposted by Danilo J. Rezende
Happy Newton’s birthday to those who celebrate
December 25, 2024 at 7:20 PM
Happy Newton’s birthday to those who celebrate
Reposted by Danilo J. Rezende
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!
December 2, 2024 at 6:36 PM
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!
Reposted by Danilo J. Rezende
This is your monthly reminder that understanding deep learning does not require rethinking generalization, and it never did.
December 18, 2024 at 12:00 AM
This is your monthly reminder that understanding deep learning does not require rethinking generalization, and it never did.
Reposted by Danilo J. Rezende
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.
December 14, 2024 at 7:15 PM
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.
More a linear algebra meme than a QM meme 😅
OK my night got away from me and I didn't post more of my students' quantum memes, so I'll do a few extra this morning!
December 7, 2024 at 4:46 PM
More a linear algebra meme than a QM meme 😅
Reposted by Danilo J. Rezende
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...
www.biorxiv.org/content/10.1...
December 6, 2024 at 8:39 AM
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...
www.biorxiv.org/content/10.1...
Reposted by Danilo J. Rezende
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
arxiv.org/abs/2209.15571
arxiv.org/abs/2303.08797
Optimal transport computes an interpolation between two distributions using an optimal coupling. Flow matching, on the other hand, uses a simpler “independent” coupling, which is the product of the marginals.
December 2, 2024 at 4:09 PM
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
arxiv.org/abs/2209.15571
arxiv.org/abs/2303.08797
Reposted by Danilo J. Rezende
🧵 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.
We want this to enable multi-disciplinary foundation model research.
December 2, 2024 at 7:46 PM
🧵 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.
We want this to enable multi-disciplinary foundation model research.
Reposted by Danilo J. Rezende
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
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
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.
arxiv.org
November 30, 2024 at 6:53 PM
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
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
Reposted by Danilo J. Rezende
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/abs/2403.14606
For the practical side, my friend @willtebbutt.bsky.social wrote stellar documentation explaining autodiff with mutation:
compintell.github.io/Mooncake.jl/...
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...
arxiv.org
November 26, 2024 at 6:05 AM
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/abs/2403.14606
For the practical side, my friend @willtebbutt.bsky.social wrote stellar documentation explaining autodiff with mutation:
compintell.github.io/Mooncake.jl/...
Reposted by Danilo J. Rezende
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/deepmind/job...
Research Engineer, Materials Science
London, UK
boards.greenhouse.io
November 25, 2024 at 4:22 PM
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/deepmind/job...
Reposted by Danilo J. Rezende
This video takes pedagogy to a whole new level in teaching the Schrödinger equation! youtu.be/uVKMY-WTrVo?...
What is the i really doing in Schrödinger's equation?
YouTube video by Welch Labs
youtu.be
November 25, 2024 at 2:50 AM
This video takes pedagogy to a whole new level in teaching the Schrödinger equation! youtu.be/uVKMY-WTrVo?...
Reposted by Danilo J. Rezende
Updated periodic table with origin of elements in the Solar System (for boron and lithium at least)
November 18, 2024 at 2:53 PM
Updated periodic table with origin of elements in the Solar System (for boron and lithium at least)