Brandon Amos

My new paper "Deep Learning is Not So Mysterious or Different": arxiv.org/abs/2503.02113. Generalization behaviours in deep learning can be intuitively understood through a notion of soft inductive biases, and formally characterized with countable hypothesis bounds! 1/12

😯

Looking for a principled evaluation method for ranking of *general* agents or models, i.e. that get evaluated across a myriad of different tasks?

I’m delighted to tell you about our new paper, Soft Condorcet Optimization (SCO) for Ranking of General Agents, to be presented at AAMAS 2025! 🧵 1/N

We've built a simulated driving agent that we trained on 1.6 billion km of driving with no human data.
It is SOTA on every planning benchmark we tried.
In self-play, it goes 20 years between collisions.

😂

Brandon is a wonderful research colleague and I could not endorse enough trying to work with Brandon

Highly recommended! I worked with Brandon, Yaron, and Ricky. Very smart, fun, and friendly crew thinking deeply about probabilistic machine learning.

Postdoctoral Researcher, Fundamental AI Research (PhD) Meta's mission is to build the future of human connection and the technology that makes it possible.

📢 My team at Meta (including Yaron Lipman and Ricky Chen) is hiring a postdoctoral researcher to help us build the next generation of flow, transport, and diffusion models! Please apply here and message me:

www.metacareers.com/jobs/1459691...

🤔 How to extract knowledge from LLMs to train better RL agents?

📚 Our new paper (w. Q. Zheng, @mikaelhenaff.bsky.social, A. Zhang, A. Grover) studies LLM-driven feedback for NetHack!

Paper: arxiv.org/abs/2410.23022
Code: github.com/facebookrese...

And unfortunately the position is only open to these four universities this cycle. Hopefully we'll be able to expand it more broadly in the future

Please get in touch if any of these topics interest you and you would like to continue developing them with us! Or if they don't interest you but you'd still like me to check with teams in other areas. Or if you just want to connect and learn more about anything :)

Our visiting students usually publish at ICML, ICLR, and NeurIPS.

My website gives an overview of the kind of research we do:

bamos.github.io

For more of a visual overview, my presentations are also available here:

bamos.github.io/presentations/

Visiting Researcher, AI Mentorship Program (PhD) Meta's mission is to build the future of human connection and the technology that makes it possible.

📢 My team at Meta is hiring visiting PhD students from CMU, UW, Berkeley, and NYU! We study core ML, optimization, amortization, transport, flows, and control for modeling and interacting with complex systems.

Please apply here and message me:

www.metacareers.com/jobs/3950223...

Here's my take on an LLM intro for our ML course at Cornell Tech (with V. Kuleshov). It starts with the foundations then goes through code to use pretrained models for 1) generation, 2) chat, and 3) code infilling.

pdf: drive.google.com/file/d/1CTGo...
ipynb: github.com/kuleshov/cor...

add bsky icon · bamos/bamos.github.io@3e5679a

I just added an icon to mine with this: github.com/bamos/bamos....

love it

here's the \mathbbmss{X} version

Wow thats actually cool to show what OT could do for you 😁

add bsky icon · bamos/bamos.github.io@3e5679a

I just added an icon to mine with this: github.com/bamos/bamos....

hi everyone!! let's try this optimal transport again 🙃