ICML DEMO Workshop Best Paper Award Runner-Up
" Practical Bayesian Optimization for Scientific Discovery " won Best Paper Award Runner-Up at ICML Workshop on Decision-Making from Offline Datasets to Online Adaptation!
News
Sort & Filters
Filters
84 results
84 results
ICML 2026 Outstanding Paper Honorable Mention
" A Random Matrix Perspective on the Consistency of Diffusion Models " by Binxu Wang, Jacob Zavatone-Veth and Cengiz Pehlevan was one of nine papers selected for outstanding paper awards or honorable mentions at ICML 2026! See news: https://blog.icml.cc...
Congratulations, Dr. Ben Ruben!
Congratulations to Dr. Ben Ruben on successfully defending his thesis in Biophysics!
A toy model to understand how AI learns
See the nice news coverage on our recent work on scaling and renormalization in high dimensional regression. https://www.eurekalert.org/news-releases/1126541 Original paper is here: https://pehlevan.seas.harvard.edu/publications/scaling-and...
ICLR 2026 Presentations from our group
Check our group's work paper at ICLR! 1 . Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time Blake Bordelon ⋅ Mary Letey ⋅ Cengiz Pehlevan 2. Discovering alternative solutions beyond the simplicity bias in recurrent neural...
NeurIPS 2025 presentations from our group members
Check the NeurIPS 2025 Presentations from our group! Main Meeting 1. Don't be lazy: CompleteP enables compute-efficient deep transformers Nolan Dey · Bin Zhang · Lorenzo Noci · Mufan Li · Blake Bordelon · Shane Bergsma · Cengiz Pehlevan · Boris Hanin ·...
Ganesh is named a Young NUS Fellow
Congratulations Ganesh for receiving the NUS Development Grant! His research on learning in biological and artificial systems was recommended by the Department of Physiology, Yong Loo Lin School of Medicine, NUS. https://www.nus.edu.sg/careers/nus...
Simons Collaboration on the Physics of Learning and Neural Computation
We are a part of a new Simons Collaboration on Physics of Learning and Neural Computation. This collaboration aims to elucidate fundamental scientific principles of learning and neural computation underlying modern artificial intelligence. To achieve...
