Tom McCoy

rtommccoy.bsky.social

14 October 2026 16:43

🤖🧠NEW PAPER🧠🤖 What is the relationship between neural networks & symbolic systems? Based on evidence from mechanistic interpretability, we argue for a quasi-symbolic view of cognition: Neural nets implement symbols but only approximately Link: www.sciencedirect.com/science/arti... 1/n

Venki Murthy

neurovenki.bsky.social

14 October 2026 13:40

Excited to share this work with Farhad Pashakhanloo, where we queried LLMs to derive the perceptual geometry of natural odor mixtures! We propose a method to predict perceptual properties from molecular composition & even steer perception in select directions by tweaking composition.

Tobias Gerstenberg

tobigerstenberg.bsky.social

12 October 2026 16:07

I'm very excited to share a new preprint with you all (5 years in the making). "Making good decisions with counterfactuals" with Ricky Ma, Scott Mueller, and Thomas Icard. We investigate how people combine experimental and observational data to make decisions. 📃 osf.io/preprints/ps...

Gaia Molinaro

gaiamolinaro.bsky.social

09 October 2026 11:11

Our reward function compression work is now out in Nature Communications! 🎉 In it, we present and empirically test a computational framework that formalizes the trade-offs between goal flexibility and learning efficiency. @annecollins.bsky.social @natureportfolio.nature.com doi.org/10.1038/s414...

Hyowon (Hyo) Gweon

hyogweon.bsky.social

06 October 2026 23:46

Just out in Cognition, with Aaron Chuey & @rbzsparks.bsky.social! Here we ask: What do children infer from watching others communicate? authors.elsevier.com/a/1ntbr2Hx32...