Congratulations to The Warren Center for Network & Data Sciences affiliate Nikolai Matni for receiving the 2024 IEEE Transactions on Control of Network Systems Best Paper Award! Matni’s work advances research in network systems, with significant implications for autonomous systems. blog.seas.upenn.edu/george-pappas-…

Check out our recent paper on layer-wise preconditioning methods for optimization and feature learning theory:

Submitting to CDC 2025 in Rio? With George Pappas, Nik Matni, and Aaron Ames, we're organizing an invited session to build on last year's CAT workshop! cat-cdc24.github.io Focus: Theory for layered architectures in complex systems If you're submitting a paper, reach out!

There’s a lot of awesome research about LLM reasoning right now. But how is  learning in the physical world 🤖different than in language 📚? In a new paper, show that imitation learning in continuous spaces can be exponentially harder than for discrete state spaces, even when

Hey Everyone!! I will be giving a lecture at the RL Theory Virtual Seminar tomorrow, on my new paper about the “Pitfalls of Imitation Learning" in continuous action spaces. 🧵 below; please read because the time is somewhat TBD..... 🧐

Accepted at #icml2025!

Huge thanks to everyone who made NESCW Columbia University awesome! The students and postdocs brought their A-game and created an incredible energy through talks and poster sessions—this is how a research community should always feel! Thrilled to host next year Princeton University! #NESCW2026 📸👇

I’m happy to share that I’ve been promoted to Associate Professor at Penn! This milestone reflects years of collaboration, mentorship, and support from so many incredible colleagues, students, friends, and family. I’m deeply grateful, and even more excited for the road ahead!

🧵generative models are sweet, but navigating existing repositories can be overwhelming, particularly when starting a new research project so i built jax-interpolants, a clean & flexible implementation of the stochastic interpolant framework in jax github.com/nmboffi/jax-in…

I’ll be presenting our paper “On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning” at ICML during the Tuesday 11am poster session! DL opt is seeing a renaissance 🦾; what can we say from a NN feature learning perspective? 1/8

I won't be attending ICML this year because of visa issues. Thomas will be presenting our work on feature learning theory + layer-wise preconditioning: