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.

📢 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...

📢 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...

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

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

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