iiinova — where your digital self keeps evolving

Reposted by Peng Qian

🤖🧠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

Top: The title, authors, and journal of the paper. Title: "Reconciling symbols and neural networks: Evidence for a quasi-symbolic view." Authors: "Tom McCoy, Abi Tenenbaum, Zhang Enyan, Zhenghao Herbert Zhou." Journal: "Current Opinion in Behavioral Sciences"

Bottom: A figure displaying how the vector representations learned by neural networks often show emergent symbolic structure. For instance, they can often be decomposed into meaningful constituents (illustrated in the figure by adding constituents to make a vector) or classified in vector space along symbolic dimensions (shown by an image of linear classifiers). However, these vectors are only quasi-symbolic: they deviate from pure symbolic structure in important ways - e.g., they can display graded similarity (“movie” is closer to “novel” than to “meal”), and they may capture graded context effects such as the word “good” affecting different nouns differently (the image shows such graded similarity among points in space

35822

Reposted by Peng Qian

Tomer Ullman @tomerullman.bsky.social · 22/09/2026

new preprint: "Directing large language models to follow the letter or spirit of the law" arxiv.org/pdf/2609.23083 (by Qian , Li, Chen, Murthy @soniakmurthy.bsky.social , Belinkov, and me) this is particularly cool/important, and I'm allowed to say it because it was headed by @pqian.bsky.social

17423

Reposted by Peng Qian

Tomer Ullman @tomerullman.bsky.social · 31/08/2026

new paper out: *~*~*~*~ "Revisiting the 5- to 7-Y ear Shift: The Age of Metacognitive Control?" (by Brod @garvinbrod.bsky.social , McAuliffe @katiemcauliffe.bsky.social , Ullman) *~*~*~*~ sharable paper link: bit.ly/5to7_2026 free pdf draft: www.tomerullman.org/papers/5to7s...

bit.ly

Revisiting the 5- to 7-year shift: The age of metacognitive control?

Abstract. The term 5- to 7-year shift refers to the marked changes in behavior observed as children transition from preschool age to school age. In 1996, a

45221

Reposted by Peng Qian

Tomer Ullman @tomerullman.bsky.social · 02/07/2026

Now out (for realz) in Cognition: "People Make Graded Judgments About The Inconceivable" (by Hu, Sosa, & me) Free preprint: www.tomerullman.org/papers/grade... Journal link: bit.ly/gradedInconCog @jennhu.bsky.social @cognitionjournal.bsky.social

17117

Reposted by Peng Qian

Lindsey Powell @lindseypowell.bsky.social · 12/04/2026

Our paper finding that infants infer helpers’ relationships, and not their dispositions, is now out in PNAS! Sharing in case anyone needs something to read on the way home from #CDS2026 ;) doi.org/10.1073/pnas...

doi.org

PNAS

Proceedings of the National Academy of Sciences (PNAS), a peer reviewed journal of the National Academy of Sciences (NAS) - an authoritative source of high-impact, original research that broadly spans...

26117

Reposted by Peng Qian

Maya Rossignac-Milon @mrossignacmilon.bsky.social · 26/03/2026

New preprint! ✨ Do you and your partner have made-up words ("eggy" to mean awkward)? Do you and your bestie have an anecdote you love to tell together (that time one of you tripped over an acorn)? Do you and your closest colleague have a cherished ritual (weekly lunch at "the usual spot")? 🧵

53915

Reposted by Peng Qian

Emily Finn @esfinn.bsky.social · 16/03/2026

Very happy that this paper from our lab is now out in @pnas.org! What happens when the *same* person experiences the *same* information with a *different* interpretation? Nearly the whole 🧠—well, at least nearly all association cortex—changes how it represents that information! tinyurl.com/p8chj2j7

tinyurl.com

PNAS

217971

Reposted by Peng Qian

Jingnan Du @jingnandu.bsky.social · 12/02/2026

I am thrilled to share that I’ll be joining the University of Notre Dame (@notredame.bsky.social) as an Assistant Professor of Psychology this July!☘️🧠 Please reach out if you're interested in joining my lab! More details to follow soon.

64713

Peng Qian @pqian.bsky.social · 20/03/2025

Do you know this work on V-information (which violates data processing inequality and can be created through computation) openreview.net/pdf?id=r1eBe...

openreview.net

110