🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

🎇My PhD thesis got approved recently! 🎇 The title is: "Scalable Bayesian Inference in the Era of Deep Learning: From Gaussian Processes to Deep Neural Networks" It is available on arXiv: arxiv.org/abs/2404.19157

InstaDeep are at #ICLR2024 this week. Please reach out to me if you would like to chat about #JAX and Large Scale ML!

Join me and my co-authors Clem Bonnet, Daniel Luo and Alex Laterre tomorrow at 10:45 to discuss Jumanji, our open-source work on high performance #RL environments in #JAX

Got lost in the #ICLR2024 poster maze? Don't worry, we've got your covered! 🛟 Here is Donal Byrne, Senior Research Engineer at InstaDeep , as he showcases Jumanji — our library for high-performance RL environments in #JAX ⭐️ Github: tinyurl.com/code-jumanji

The shamer is apparently too obsessed with conformal prediction as if everything else is BS. Someone please tell the person that the VAE paper just won the test of time award at ICLR, and that the loss function in diffusion models is akin to the ELBO in variational Bayes

Stanford and Berkeley students start companies at 5x the rate of Oxford and Cambridge. Why the smartest, most technical people in the UK should take more risk 🚀 tomblomfield.com/post/750852175…

In our latest preprint, we introduce an efficient, alchemical free energy method compatible with maching learned forcefields, enabling calculation of hydration free energies with first principles accuracy! (1/5)

Why you should visit Cape Town, South Africa marginalrevolution.com/marginalrevolu…

Super excited to announce Ångström AI, our startup using Gen AI to build fast and experimentally accurate simulations of molecular interactions together with Laurence Midgley, Jose Miguel Hernández-Lobato and Gabor Csanyi. We are backed by Y Combinator! See below for a simulation demo (1/3)🧵.

I made my first ever investment in a startup, Ångström AI They build on ML surrogate models to enable cost-effective simulation of molecular properties (e.g. solubility or binding) in pharmacologically relevant settings. A very hard technical problem that this team might crack.

I'm excited to share that I’ll present my research at #NeurIPS as a self-employed, independent researcher!🎉 Having limited resources, I’m seeking support or funding to help me attend. Any assistance or leads would be greatly appreciated! 🙏 Thank you!! #AI #Research

Introducing Latent Program Network (LPN), a new architecture for inductive program synthesis that builds in test-time adaption by learning a latent space that can be used for search 🔎 Inspired by ARC Prize 🧩, we designed LPN to tackle out-of-distribution reasoning tasks!

Best illustrations award!

Sick demo!!!

Highly recommend trying out the quick demo to understand Latent Program Networks. I guarantee it's fun!! Demo HF space: huggingface.co/spaces/clement…

Very fortunate to have received the third-place paper award of ARC Prize with Matthew Macfarlane!! 🏆 Amazing efforts from François Chollet Mike Knoop and the team to have made working on ARC-AGI such a success 🔥 Excited for 2025!!

We spoke with Clem Bonnet at NeurIPS about his extremely innovative approach to the ARC Prize using a form of test time inference where you search a latent space of a VAE before making an optimal prediction. François Chollet was so impressed, he hired Clem shortly after! 😃 -

I had a fantastic time discussing latent search with Tim Scarfe on MLST! 🙏 We review our work on latent program networks co-authored with Matthew Macfarlane and debate composition, AI creativity, and program synthesis. Full video: youtu.be/PHBItVuudbU