How can the brain learn the hidden hierarchical structure from high dimensional data? In our latest work, we use synthetic datasets to analyze two classes of bio-plausible learning rules: variants of Direct Feedback Alignment, and local self-supervised learning. We find only the latter succeeds.

Show Post

Interested in multitasking RNNs from a theory perspective? Check out this preprint with the amazing @lpezon.bsky.social. TLDR: A low-rank / latent space approach to @lndriscoll.bsky.social & @sussillodavid.bsky.social style shared components. And a story starring solution space degeneracy.

Show Post

Accepted at ICML 2026. I am extremely proud of this work. Local learning is starting to work really well! The theoretical perspective of local learning minimizing an emergent global objective has been eye opening Congrats @zihan-wu.bsky.social and Ariane Delrocq! Great team

Show Post

More evidence, from a large-scale study in China, that using AI hurts learning if it undermines mental effort. When homework time drops due to AI use, so do test scores. Across studies, there is a clear theme: AI tutoring in support of classes is good, using AI to "help" with homework is bad.

Show Post

NEW PAPER. Why do larger networks train better? "Because they contain more candidate *sub*networks that can learn the task" → lottery tickets This popular explanation uses an appealing but misleading metaphor🧵 We propose an intuitive alternative grounded in theory: escape dimensions

Show Post