Cosmin Paduraru

Research scientist @DeepMind, here to see what's going on in the world and what @samuelpepys is up to

[Cosmin Paduraru @CauseMean]

@andreamichi @depthfirstlabs Awesome job getting agentic RL to work so we'll!

[Cosmin Paduraru @CauseMean]

@andreamichi So happy you guys are doing this, I can (almost) forgive you for leaving DeepMind

[Cosmin Paduraru @CauseMean]

@andreamichi @depthfirstlabs Awesome! This is very timely and important

[Cosmin Paduraru @CauseMean]

@LauraFlowD @Liv_Boeree https://t.co/h5UN6jxjm4

[Marc G. Bellemare @marcgbellemare]

Interested in using reinforcement learning to train LLMs for problems where there’s no room for error? Do you want to build massive data pipelines to transform how we interact with scientific knowledge?

We're hiring for multiple roles at Reliant:

https://t.co/hzTqp6Z6To

[SNW @SamanthaWork]

Congrats team!

[Marc G. Bellemare @marcgbellemare]

Love to build ML software?

Reliant AI is hiring in Montreal.
https://t.co/VbSueicFlx

[Cosmin Paduraru @CauseMean]

This is such a powerful, emotional and important movie. Thanks Oz for everything you've done to tell the world what's happening in Ukraine

[Oz Katerji @OzKaterji]

A dear filmmaker friend of mine recently congratulated me & said "you have achieved what 95% of filmmakers never achieve - you have actually made a film."

My directorial debut The Battle for Kyiv premieres in London in less than 48 hours, and I can't wait to share it with you.

[Cosmin Paduraru @CauseMean]

Really enjoyed working on this. Perfect problem fit for RL, technically challenging in many ways, and hopefully a step towards making tokamak fusion practical

[Andrea Michi @andreamichi]

Our paper on using RL for tokamak magnetic control has been recently published on the Fusion Engineering and Design journal. And while this is not about the latest LLMs, there are quite a few lessons learned on how to make RL work in applied domains

https://t.co/tEsrXUGbu6

[Olivia W @OliviaW47557022]

Student researcher position applications are open at Google Deepmind!

I'm hosting a SR in the intersection of bias and generative models. If you're an interested PhD student please reach out!

https://t.co/dKPbGByGEb…

[Simon Geisler @geisler_si]

Today I am going to present our work on transformers for directed graphs in the Learning on Graphs and Geometry reading group.

Joint work with @liyuajia @DJ_Mankowitz @TaylanCemgilML @guennemann @CauseMean

[Simon Geisler @geisler_si]

Are you interested in transformers and/or graphs and are at #ICML2023? Then visit me at poster session 1 (25 Jul 11 a.m.), where I present our @DeepMind paper Transformers Meet Directed Graphs.

Joint work work with @liyuajia @DJ_Mankowitz @TaylanCemgilML @guennemann @CauseMean

[Simon Geisler @geisler_si]

The transformer architecture powers recent AI tools like #ChatGPT or #GoogleBard.

In our @DeepMind #ICML2023 paper Transformers Meet Directed Graphs, we generalize transformers to more general inputs, namely directed graphs.

Here’s how we did it. 🧵 https://t.co/2wpv4n0uPN

[Cosmin Paduraru @CauseMean]

@pfau Fun now do one on gain of function research

[Google DeepMind @GoogleDeepMind]

Our AI started with games. ♟️ But it didn’t end there. 🌐

Meet MuZero and AlphaZero, two powerful models which have evolved to transform computing itself. They’re already optimising data centres, improving the way we watch videos, and much more.

How? 🧵 https://t.co/NOq3uY3rJm

[Cosmin Paduraru @CauseMean]

https://t.co/MerJI3mH2G I would also like to thank everyone who contributed to this work. It was a privilege (and lots of fun) working with you all!

[Google DeepMind @GoogleDeepMind]

Work by: @DJ_Mankowitz, @andreamichi, @AZhernov, Marco Gelmi, @macselvi, @eleurent, @CauseMean, @shariqbal, Jean-Baptiste Lespiau, Alex Ahern, Thomas Koppe, Kevin Millikin, Stephen Gaffney, Sophie Elster, Jackson Broshear, Chris Gamble, Kieran Milan, Robert Tung, Minjae Hwang…

[Cosmin Paduraru @CauseMean]

Our @Nature work on using #AlphaDev, an extension of AlphaZero, to improve the efficiency of fundamental algorithms such as sorting and hashing is out today! See @DeepMind post at https://t.co/b4UHwBMOZx, and a few things I found interesting about it in 🧵

[Cosmin Paduraru @CauseMean]

Our neural network was a relatively small transformer trained only on assembly code generated by AlphaZero during its search process, showing that AI can still produce breakthrough results without very large pretrained models