Profile avatar
vmoens.bsky.social
Research Engineer - PyTorch core - Meta@London - Open-source/open science advocate Maintainer of torchrl / tensordict / leanrl Former MD - Neuroscience PhD https://github.com/vmoens
85 posts 1,917 followers 638 following
Regular Contributor
Active Commenter
Posts 18 Comments 32

Today we're opensourcing MLGym, an API for AI research agents. MLGym relies on a gym environment that wraps a docker image. Each env has a task specified as a YAML file, telling in plain english what you want your LLM to achieve 👇

submitted 5 days ago • 1 comment

A few tips I share when I talk about perf with PyTorch in eager mode (with focus on small models): 🪢

submitted 7 days ago • 1 comment

I stand by my point that the word "agent" should be avoided at all costs. At least in RL, anytime I see an "Agent" class it's meant to be a "whatever doesn't fit in any other bucket in my codebase".

submitted 15 days ago • 2 comments

Everyone's like "hey I just coded and trained a SOTA LLM in my garage last week, also wrote a blogpost about it and opensourced the repo" and the only thing I did in the meantime was fix a CI and configure a remote interpreter on a server... 😢

submitted 20 days ago • 0 comments

A new release of tensordict is out github.com/pytorch/tens... Thanks to all who have contributed!

submitted 21 days ago • 1 comment

Clap hands if you were doing RL before it was cool

submitted 29 days ago • 0 comments

You’ve never really understood PyTorch until you’ve figured out what torch.scatter exactly does. I’ve never really understood PyTorch.

submitted 31 days ago • 1 comment

Introducing playground.mujoco.org Combining MuJoCo’s rich and thriving ecosystem, massively parallel GPU-accelerated simulation, and real-world results across a diverse range of robot platforms: quadrupeds, humanoids, dexterous hands, and arms. Get started today: pip install playground

submitted 41 days ago • 1 comment

One of the bests Mindscape episodes I've heard! I've always been interested in the epistemology of controversial scientific concepts such as emergence or consciousness. Vaguely defined concepts (or diverging definitions) are often at the root of many pointless debates. Kudos on clarifying things!

submitted 48 days ago • 0 comments

New Year’s resolutions: - eat healthier - exercise more - no more “is all you need” papers

submitted 67 days ago • 2 comments

Yesterday the hyped Genesis simulator released. But it's up to 10x slower than existing GPU sims, not 10-80x faster or 430,000x faster than realtime since they benchmark mostly static environments blog post with corrected open source benchmarks & details: stoneztao.substack.com/p/the-new-hy...

submitted 67 days ago • 4 comments

Wrong answers only: What does this `Human-computer` sticker seen at neurips hide?

submitted 69 days ago • 3 comments

Check out Motivo, a behavioral foundation model for humanoid control by FAIR. It's a one-of-its-kind unsupervised RL project, and it comes with a demo that is SO fun to play with! metamotivo.metademolab.com (for the record, they use compile and cudagraphs -> github.com/facebookrese...)

submitted 74 days ago • 1 comment

I’m 100% sure this button never does anything

submitted 75 days ago • 0 comments

PyTorch has released torchcodec yesterday, a powerful video decoding toolbox pytorch.org/blog/torchco... github.com/pytorch/torc...

submitted 76 days ago • 1 comment

Tomorrow with Matteo Bettini we'll be presenting BenchMARL at #NeurIPS (@neuripsconf.bsky.social) in #Vancouver

submitted 77 days ago • 1 comment

I'm excited to be in #Vancouver for #NeurIPS 2024 where I brought a bunch of @LEGO_Group bricks in my bag! *no, I'm not Santa!

submitted 79 days ago • 2 comments

We’re looking for an intern (research scientist/PhD) to join the PyTorch team in NYC this summer and work on GPU kernel generation, more info here: www.metacareers.com/jobs/6044463... You’ll be working with @soumithchintala.bsky.social, @marksaroufim.bsky.social and myself

submitted 81 days ago • 1 comment