iiinova — where your digital self keeps evolving

Reposted by Valerio Pepe

Sam Gershman @gershbrain.bsky.social · 09/01/2026

With some trepidation, I'm putting this out into the world: gershmanlab.com/textbook.html It's a textbook called Computational Foundations of Cognitive Neuroscience, which I wrote for my class. My hope is that this will be a living document, continuously improved as I get feedback.

16590237

Reposted by Valerio Pepe

Ev Fedorenko @evfedorenko.bsky.social · 26/11/2025

It has been so so fun to think with some of my favorite scientists about what it means to understand!

0539

Reposted by Valerio Pepe

Gabe Grand @gabegrand.bsky.social · 27/10/2025

Do AI agents ask good questions? We built “Collaborative Battleship” to find out—and discovered that weaker LMs + Bayesian inference can beat GPT-5 at 1% of the cost. Paper, code & demos: gabegrand.github.io/battleship Here's what we learned about building rational information-seeking agents... 🧵🔽

12411

Valerio Pepe @valeriopepe.bsky.social · 28/10/2025

I'm really excited about this work (two years in the making!). We look at how LLMs seek out and integrate information and find that even GPT-5-tier models are bad at this, meaning we can use Bayesian inference to uplift weak LMs and beat them... at 1% of the cost 👀

030

Reposted by Valerio Pepe

Kanishka Misra @kanishka.bsky.social · 16/10/2025

"Although I hate leafy vegetables, I prefer daxes to blickets." Can you tell if daxes are leafy vegetables? LM's can't seem to! 📷 We investigate if LMs capture these inferences from connectives when they cannot rely on world knowledge. New paper w/ Daniel, Will, @jessyjli.bsky.social

Title page of the paper: WUGNECTIVES: Novel Entity Inferences of Language Models from Discourse Connectives, with two figures at the bottom

Left: Our figure 1 -- comparing previous work, which usually predicted the connective given the arguments (grounded in the world); our work flips this premise by getting models to use their knowledge of connectives to predict something about the world.

Right: Our main results across 7 types of connective senses. Models are especially bad at Concession connectives.

2329

Reposted by Valerio Pepe

Ben Recht @beenwrekt.bsky.social · 23/09/2025

It’s week 4 and probably time to start doing machine learning in machine learning class. We begin with the only nice thing we have: the perceptron.

argmin.net

Common Descent

Machine learning begins with the perceptron

0393

Valerio Pepe @valeriopepe.bsky.social · 08/06/2025

New blog post! www.lesswrong.com/posts/qHudHZ... Following Emergent Misalignment, we show that finetuning even a single layer via LoRA on insecure code can induce toxic outputs in Qwen2.5-Coder-32B-Instruct, and that you can extract steering vectors to make the base model similarly misaligned 🧵

lesswrong.com

Emergent Misalignment on a Budget — LessWrong

TL;DR We reproduce emergent misalignment (Betley et al. 2025) in Qwen2.5-Coder-32B-Instruct using single-layer LoRA finetuning, showing that tweaking…

110

Reposted by Valerio Pepe

Hokin @hokin.bsky.social · 24/05/2025

Sam is 100% correct on this. Indeed, human babies have essential cognitive priors such as permanence, continuity, and boundary of objects, 3D Euclidean understanding of space, etc. We spent 2 years to systematically to examine and show the lack of such in MLLMs: arxiv.org/abs/2410.10855

0215

Reposted by Valerio Pepe

Sam Gershman @gershbrain.bsky.social · 19/05/2025

I think the BabyLM Challenge is really interesting, but also feel that there is something fundamentally ill-posed about how it maps onto the challenge facing human children. It's true that babies only get a relatively limited amount of linguistic experience, but...

3407

Reposted by Valerio Pepe

Cognition @cognitionjournal.bsky.social · 20/05/2025

Word learning is usually about what a word does refer to. But can toddlers learn from what it doesn’t? Our new Cognition paper shows 20-month-olds use negative evidence to infer novel word meanings, reshaping theories of language development. www.sciencedirect.com/science/arti...

03312

Reposted by Valerio Pepe

Damien Masson @damienhci.bsky.social · 18/03/2025

Photoshop for text. In our #CHI2025 paper “Textoshop”, we explore how interactions inspired by drawing software can help edit text. We consider words as pixels, sentences as regions, and tones as colours. #HCI #NLProc #LLMs #AI Thread 🧵 (1/10)

25316

Valerio Pepe @valeriopepe.bsky.social · 28/01/2025

saw a new pika model was out on twitter & robot-gasoline-bench does not disappoint

120

Reposted by Valerio Pepe

Griffiths Computational Cognitive Science Lab @cocoscilab.bsky.social · 18/11/2024

(1/5) Very excited to announce the publication of Bayesian Models of Cognition: Reverse Engineering the Mind. More than a decade in the making, it's a big (600+ pages) beautiful book covering both the basics and recent work: mitpress.mit.edu/978026204941...

14521120

Valerio Pepe @valeriopepe.bsky.social · 16/11/2024

Hello bsky! I'm Valerio, an undergrad at Harvard studying computer science and cognitive science. I'm interested in the inductive biases that make language learning and reasoning so easy for us humans, and what their analogues are in machines. If you're around Boston, I would love to grab coffee!

030

Reposted by Valerio Pepe

xuan (ɕɥɛn / sh-yen) @xuanalogue.bsky.social · 11/11/2024

Okay the people requested one so here is an attempt at a Computational Cognitive Science starter pack -- with apologies to everyone I've missed! LMK if there's anyone I should add! go.bsky.app/KDTg6pv

7021991

Valerio Pepe @valeriopepe.bsky.social · 29/09/2023

Excited to share this article I authored with Merrick Pierson Smela and George Church at the Wyss Institute! We present SeqVerify, the first automated pipeline for quality-control of whole-genome sequencing data, for all your stem-cell needs!

040