Jakeup Nick opentheory.net/2023/07/princi…

Object slots are great for compositional generalization, but can models without these inductive biases learn compositional representations without supervision too? Yes! Unsupervised learning on object videos yields entangled, yet compositional latent codes for objects!

If anyone among you is at EWRL, Toulouse, let's meet up!

What weird audio latent spaces are you currently inhabiting? Me open.spotify.com/album/3kH1Vfvp…

At Chandar Lab, we are happy to announce the second edition of our assistance program to provide feedback for members of communities underrepresented in AI who want to apply to high-profile graduate programs. Want feedback? Details: chandar-lab.github.io/grad-app-help/. Deadline: Nov 15!

If you’re considering moving on from this garbage feed, AI bksy is hitting its hockey stick era

Bluesky is hitting a big threshold of ml people migrating from this garbage pile! Join us there!! So many stater packs to fill your feed without puppet master throwing political garbage at you.

We are very excited to announce Kinetix: an open-ended universe of physics-based tasks for RL! We use Kinetix to train a general agent on millions of randomly generated physics problems and show that this agent generalises to unseen handmade environments. 1/🧵

SIMPL outperforms CEBRA — a contemporary, more general-purpose, neural-net-based technique — in terms of performance and compute-time. It’s over 30x faster. 12/21

Roger Creus Castanyer just implemented a CleanRL Parallel Q-Networks algorithm (PQN) implementation! 🚀PQN is DQN without a replay buffer and target network. You can run PQN on GPU environments or vectorized environments. E.g., in envpool, PQN gets DQN's score in 1/10th the time

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!

Lol my ML/AI feed here is growing more silent and has more or less shifted to bsky completely. Join us there 🦋

My bsky feed now has more signal than here. Looks more and mote like it's so over here with probability> 90% let's see.

DARK lab is now also on That Other Place 🦋. Our members are already actively discussing AI on the butterfly. Come be one of our first followers! Handle: UCL-DARK

Happening now, come by! West Ballroom A-D #6404 📅12 Dec 4:30 PM — 7:30 PM

The data science revolution is getting closer. TabPFN v2 is published in Nature: nature.com/articles/s4158… On tabular classification with up to 10k data points & 500 features, in 2.8s TabPFN on average outperforms all other methods, even when tuning them for up to 4 hours🧵1/19

Excited to share that I’ll be starting as a postdoc in Rose Bagot's lab at McGill University , studying the neural mechanisms of psychedelics ✨🐁🌀 Grateful for this new adventure.

🚨 Excited to share our new work: "Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning"! 📈 We propose gradient interventions that enable stable, scalable learning, achieving significant performance gains across agents and environments! Details below 👇

really excited about this new work we just put out, led by my students Roger Creus Castanyer & Johan S. Obando 👍🏽 , where we examine the challenges of gradient propagation when scaling deep RL networks. roger & johan put in a lot of work and care in this work, check out more details in 🧵👇🏾 !