iiinova — where your digital self keeps evolving

Reposted by Daniel Wurgaft

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

17322

Reposted by Daniel Wurgaft

Tobias Gerstenberg @tobigerstenberg.bsky.social · 16/09/2026

Excited and grateful to be part of this initiative by the Toyota Research Institute 🙏 Together with Thomas Icard, @noahdgoodman.bsky.social, and @yangxiang.bsky.social our team will explore what role responsibility plays in supporting effective collaboration. 📃 www.tri.global/news/elevati...

tri.global

Elevating Human Growth: Human-AI Kaizen Initiative | Toyota Research Institute

By Matthew Lee, Program Director, Human-AI Kaizen Initiative Today, Toyota Research Institute (TRI) announces the proposals selected for the Human-AI Kaizen Initiative, a multi-year collaboration with...

0202

Reposted by Daniel Wurgaft

Russ Poldrack @russpoldrack.org · 29/08/2026

*Sharing for our department’s trainees* 🧠 Looking for insight on applying to PhD programs in psychology? ✨ Apply by Sep 21st to Stanford Psychology's 10th annual Paths to a Psychology PhD info session/workshop to have all of your questions answered! 📝 Application: forms.gle/4nujgDd3W2tx...

forms.gle

Paths to a Psychology Ph.D.: An Information Session and Workshop

Join Stanford Psychology graduate students, research assistants, and faculty for a free one-day virtual information session and workshop on applying to research positions and Ph.D. programs in psychol...

01515

Reposted by Daniel Wurgaft

Irmak Ergin @irmakergin.bsky.social · 28/08/2026

Had a great time presenting our work at #CCN2026 last month! Extended abstract: openreview.net/pdf?id=dGLdG... Talk recording, alongside other great ECR talks in the Audition & Language session: www.youtube.com/watch?v=PavZ... If you'd like to chat about our research, you can find me at #SNL2026

091

Reposted by Daniel Wurgaft

Lucas Benjamin @lucaswbenjamin.bsky.social · 24/08/2026

Our new paper is now out in @pnas.org! How does the (baby) brain extract regularities from sequences from what-follows-what up to large-scale network structure? What if it all came from a single mechanism? www.pnas.org/doi/abs/10.1...

15216

Reposted by Daniel Wurgaft

Arthur Prat @arthurpr4t.bsky.social · 21/08/2026

We broke Weber's law. By manipulating the prior (ie the frequencies of small and large magnitudes), we changed how people's accuracy depended on magnitude. When large magnitudes were more frequent, subjects became more precise about them. This points to efficient coding, dynamically implemented.

15515

Reposted by Daniel Wurgaft

Ida Momennejad @neuroai.bsky.social · 19/08/2026

📣Algorithmic Grammar of Flexible Cognition: A Walk through Latent Operations osf.io/preprints/ps... Flexible behavior moves adaptively btwn cognitive modes. But units of analysis remain representations & few operations. Proposal: formalize open-ended cognition as walk over latent operations 1/n

18121

Reposted by Daniel Wurgaft

Sam Nastase @samnastase.bsky.social · 18/08/2026

New perspective piece out in @cp-neuron.bsky.social with Zaid Zada, @adelegoldberg.bsky.social, and Uri Hasson! We try to articulate some of our excitement about LLMs and discuss what kinds of insights they might provide into the neural computations supporting natural language in the human brain.

18625

Reposted by Daniel Wurgaft

Andrew Lampinen @lampinen.bsky.social · 14/08/2026

New position piece w/ @tylerbonnen.bsky.social out now in COBS! We suggest that data augmentation is a useful framework for understanding hippocampal contributions to generalization, and offers a path towards more precise modeling: 1/

Data augmentation as a framework for modeling hippocampal contributions to generalization

14814

Reposted by Daniel Wurgaft

Sam Gershman @gershbrain.bsky.social · 10/08/2026

Cool work by @amirzur.bsky.social, @rdhawkins.bsky.social and their collaborators replicating our finding on causal implicatures from correlational language, and showing that this can arise from rational pragmatic inference: escholarship.org/content/qt60...

1113

Reposted by Daniel Wurgaft

Verona Teo @veronateo.bsky.social · 06/08/2026

Deciding when to jump in and help someone—and when to hold back and let them work through it—is something humans navigate constantly. How do AI assistants handle this tradeoff? We introduce Int-Bench, a framework for evaluating interventions during problem-solving tasks.

3234

Reposted by Daniel Wurgaft

Aran Nayebi @anayebi.bsky.social · 04/08/2026

Version 2 of Theory of Contravariance w/ @dyamins.bsky.social is out! New material on contravariance for Transformers, and the theory of Representational Similarity Analysis (RSA) and centered kernel analysis (CKA)/Procrustes.

3155

Reposted by Daniel Wurgaft

Minds, Machines, and Brains (MMB) @mmb-journal.bsky.social · 02/08/2026

Hello world! 👋 We’re Minds, Machines, and Brains (MMB) 👤🤖🧠 a new open access journal from @mitpress.bsky.social exploring the principles of intelligence and cognition across natural and artificial minds. Submissions open this Fall! 🔗 direct.mit.edu/mmb

direct.mit.edu

Minds, Machines, and Brains | MIT Press

223793

Reposted by Daniel Wurgaft

Ben Prystawski @benpry.bsky.social · 23/07/2026

How do people learn abstract knowledge over generations in a crafting game with rich structure? Come by my talk in the cultural evolution session on Friday morning at #CogSci2026 to find out!

1175

Daniel Wurgaft @danielwurgaft.bsky.social · 22/07/2026

go check out @benpry.bsky.social talking about our think aloud work and automated discovery of cognitive models!

040

Reposted by Daniel Wurgaft

Charley Wu @thecharleywu.bsky.social · 22/07/2026

The framing-the-problem.github.io/cogsci2026.h... workshop at #cogsci2026 is kicking off with an intro from @hanqizhou.bsky.social Come find us in Galvea B

0163

Reposted by Daniel Wurgaft

Russ Poldrack @russpoldrack.org · 18/07/2026

I've posted a preprint of a philosophical paper I've written on the relationships between understanding, prediction, and compression, based on a talk I gave at SPAN 2025. Now in press at Synthese. philarchive.org/archive/POLUPA

philarchive.org

04814

Reposted by Daniel Wurgaft

Linas Nasvytis @linasnasvytis.bsky.social · 26/06/2026

Incredibly excited about this direction: automating scientific discovery in cognitive science, with agents designing targeted experiments, collecting human data, and using the results to refine their theories. We show that this loop can lead to models that better predict human behavior!

061

Reposted by Daniel Wurgaft

Mike Frank @mcxfrank.bsky.social · 26/06/2026

Fun story about this paper, which I'm really excited about! This came out of a classic nerdswipe by @noahdgoodman.bsky.social - we were teaching together this winter and he said "is it time for robots to do psychology?"

182

Reposted by Daniel Wurgaft

Kushin Mukherjee @kushinm.bsky.social · 26/06/2026

Really proud to be part of this dream team! We make a strong case for end-to-end systems that can not only propose new cognitive theories but *validate* them by collecting human data! ✨ Check out project lead Ben’s thread for the highlights and a link to our preprint!

041

Reposted by Daniel Wurgaft

Ben Prystawski @benpry.bsky.social · 26/06/2026

New preprint! AI agents have shown impressive scientific automation capabilities. Can we apply them to psychology research, *including* human data collection? We introduce auto-psych, a framework that proposes cognitive models and uses them to design and run human experiments. 1/

2427

Reposted by Daniel Wurgaft

Samah Abdelrahim | سماح @samahrahim.bsky.social · 24/06/2026

1st published paper alert ⚠️ in which @mcxfrank.bsky.social and I ask: How robust is the “shape bias”? a phenomenon that has been central to theories of early word learning: If a child hears a new word for an object, they often extend it to other objects with the same shape. tinyurl.com/JCL-shapebias

cambridge.org

Examining the Robustness and Generalizability of the Shape Bias: A Meta-Analysis | Journal of Child Language | Cambridge Core

Examining the Robustness and Generalizability of the Shape Bias: A Meta-Analysis

1324

Reposted by Daniel Wurgaft

Akshay K. Jagadish @akjagadish.bsky.social · 22/06/2026

1/ 🚨 New opinion piece: "Can we automatize scientific discovery in the cognitive sciences?" We lay out a vision for a fully automated, in-silico science of the mind, where modern AI systems run every stage of the scientific discovery cycle in cognitive science 🧵 #AutomatedDiscovery #AI4Science

1186

Reposted by Daniel Wurgaft

Liu, Shuze @liushuze.bsky.social · 18/06/2026

Join us at both conferences this summer! Our #CogSci2026 workshop features a series of invited talks on problem representations and abstractions. Our #CCN2026 community event opens a broader discussion on naturalistic problem solving: frameworks, tasks, methods, and where the field should go next.

0195

Reposted by Daniel Wurgaft

Michael Lepori @michael-lepori.bsky.social · 09/06/2026

🚨New preprint!🚨 We know that LM representations can be used to predict brain responses to language. But what *features* of these representations underlie this alignment? We use SAEs to find out!

1255

Reposted by Daniel Wurgaft

Linas Nasvytis @linasnasvytis.bsky.social · 08/06/2026

1/ New preprint! Reasoning models often require hundreds of task examples and thousands of rollouts to improve on a task. How can they learn more from much less? Introducing CORE: contrastive self-reflection for rapid, sample-efficient, and interpretable self-improvement 🧵

2307

Reposted by Daniel Wurgaft

Tom McCoy @rtommccoy.bsky.social · 22/05/2026

🤖🧠NEW PAPER🧠🤖 Children & neural networks can learn syntax from linear strings of words. How do they do it? Our hypothesis: Word co-occurrence statistics provide cues to syntax! (I.e., a new type of bootstrapping to consider!) Paper: arxiv.org/abs/2605.20529 1/n

Paper overview.
Title: "Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks"
Authors: Claire Hobbs and Tom McCoy
Method: We trained many neural nets, varying how predictable a subject is given its verb. We tested them on subject-verb agreement
Findings: With the right level of predictability, neural networks robustly generalize. The predictability of child-directed language is near the neural net optimum.
Conclusion: Statistical regularities in word co-occurrence can support the learning of abstract syntactic rules
The text is accompanied by a graph showing neural-network accuracy as a function of the level of variability; the accuracy peaks at an in-between level of variability

2395

Reposted by Daniel Wurgaft

Josh Wilson @norcalneuro.bsky.social · 22/05/2026

1/ New preprint with @dyamins.bsky.social + team! Ventral visual representations within areas evolve over the course of the response along the same hierarchical complexity axis that distinguishes the visual areas, potentially driven by local recurrence.

1164

Reposted by Daniel Wurgaft

Linas Nasvytis @linasnasvytis.bsky.social · 19/05/2026

1\ Can you make this Roman-numeral equation true by moving exactly one matchstick?

2236

Reposted by Daniel Wurgaft

Mike Frank @mcxfrank.bsky.social · 18/05/2026

What is a psychological theory? Here's our take on this tricky and controversial question in this week's Experimentology chapter summary. Many things called "theories" in psychology aren't actually theories — they're frameworks. 🧵 experimentology.io

312752

Reposted by Daniel Wurgaft

Justin Yang @justintheyang.bsky.social · 13/05/2026

Thrilled to be sharing my latest work at #CogSci2026! Many of the spaces we move through, from kitchens to airports, were designed with specific uses in mind. How do people create such environments, and how do users figure out what they were designed for? 📃 osf.io/preprints/ps...

25112

Reposted by Daniel Wurgaft

Mike Frank @mcxfrank.bsky.social · 11/05/2026

Many of us were taught experiments are for testing hypotheses. In Ch 1 of Experimentology, our free, open methods textbook, my coauthors and I argue differently: experiments are for estimating the magnitude of causal effects. This reframing has important consequences. 🧵 experimentology.io

612932

Reposted by Daniel Wurgaft

Kanishka Misra @kanishka.bsky.social · 11/05/2026

New opinion piece on the interface between research on concepts and categories in minds vs. in neural network LMs! I take the position that there is much to be learned from this interface (e.g., learning about concepts from language alone) and outline some directions for future.

Title page of "Semantic Cognition for and from Language Models" followed by a figure showing tests that target conceptual structure and content vs. those that target function.

25712

Reposted by Daniel Wurgaft

Naomi Saphra @nsaphra.bsky.social · 08/05/2026

Goodfire released a megapost of all the random feature geometry stuff they're finding, and it's worth a read

goodfire.ai

The World Inside Neural Networks

How neural geometry will unlock understanding and control of AI

213126

Reposted by Daniel Wurgaft

Charley Wu @thecharleywu.bsky.social · 27/04/2026

🚨 New preprint w/ Valerio Rubino and Peter Dayan: how do people discover and use compositional structure under constraints? osf.io/preprints/ps... A key factor is a simple heuristic that favors reuse of repeated and symmetric fragments across scales, is robust to time pressure, and sped up RTs 🧵👇

110233

Reposted by Daniel Wurgaft

Jean-Rémi King @jeanremiking.bsky.social · 21/04/2026

We're happy to release NeuralSet: a simple, fast, scalable package for Neuro-AI Supports: 🧠 fMRI, EEG, MEG, iEEG, spikes… preprocessing 💬 text 🔊 audio ▶️ video 🏞️ image… embeddings 📦 pip install neuralset 🔍 facebookresearch.github.io/neuroai/neur... 📄 kingjr.github.io/files/neural... 🧵 Details👇

17530

Reposted by Daniel Wurgaft

Kanishka Misra @kanishka.bsky.social · 17/04/2026

Announcing a new version of our 2024 paper on linguistic hypothesis generation from LMs! @najoung.bsky.social and I have systematized our hypothesis generation framework, added stringent criteria for model selection, 10x-ed our learning trials, and included an epigraph from Jeff Elman 🙏!

Title page for the paper “A systematic framework for generating novel experimental hypotheses from language models”, with an epigraph from Jeff Elman describing how Rumelhart and McClelland (1982) did hypothesis generation with their connectionist network, and a figure describing our pipeline.

1195

Reposted by Daniel Wurgaft

Khai Loong Aw @khaiaw.bsky.social · 14/04/2026

Children exhibit visual understanding from limited experience, orders of magnitude less than our best models. We introduce the Zero-shot World Model (ZWM). Trained on a single child's visual experience, BabyZWM rapidly generates competence across diverse benchmarks with no task-specific training. 🧵

15724

Reposted by Daniel Wurgaft

Mike Frank @mcxfrank.bsky.social · 06/04/2026

Come join us! We have two research coordinator positions open with the Stanford IRISS predoctoral program, a program designed to mentor students for graduate study: LEVANTE: careersearch.stanford.edu/jobs/iriss-p... BabyView: careersearch.stanford.edu/jobs/iriss-p... (deadline 5/1)

careersearch.stanford.edu

IRiSS Predoctoral Researcher in School of Humanities and Sciences, Stanford, California, United States

The Stanford Institute for Research in the Social Sciences (IRiSS) is seeking Predoctoral Researchers to participate in our 2026-2027 cohort. The...

03632

Reposted by Daniel Wurgaft

Judy Fan @judithfan.bsky.social · 08/04/2026

The Cognitive Tools Lab at Stanford (cogtoolslab.github.io) is recruiting two new research staff members to join in AY 26-27. Full-Time Lab Manager: forms.gle/UVwfx5wbY9Km.... IRiSS Predoc Researcher: iriss.stanford.edu/predoc/2026-.... Please share widely in your networks, thank you!!

cogtoolslab.github.io

about the lab – cognitive tools lab

25242

Reposted by Daniel Wurgaft

Tobias Gerstenberg @tobigerstenberg.bsky.social · 03/04/2026

The Causality in Cognition Lab -- a supportive, bluesky-colored team -- is looking for a predoc to join us! Here are infos about the lab (cicl.stanford.edu) and the position (careersearch.stanford.edu/jobs/iriss-p...). The application deadline is May 1st. Please share, thank you 🙏

26536

Reposted by Daniel Wurgaft

Irmak Ergin @irmakergin.bsky.social · 01/04/2026

Excited to share our new publication, “Measuring Naturalistic Speech Comprehension in Real Time”! ➡️ rdcu.be/fa3hk #psynomBRM w/ @kriesjill.bsky.social, Shiven Gupta, Maria Papworth Burrel, & @lauragwilliams.bsky.social 🧵1/11

rdcu.be

Measuring naturalistic speech comprehension in real time

13111

Reposted by Daniel Wurgaft

Jared Moore @jaredlcm.bsky.social · 18/03/2026

Disturbing anecdotal reports of "AI psychosis" and negative psychological effects have been emerging in the news. But what actually happens during these lengthy delusional "spirals"? In our preprint, we analyze chat logs from 19 users who experienced severe psychological harm🧵👇

3224131

Reposted by Daniel Wurgaft

Jared Moore @jaredlcm.bsky.social · 10/03/2026

Can LLMs use ToM to genuinely persuade you, or do they just use good rhetoric? In our new preprint, we use the MINDGAMES framework to test this. Surprisingly, LLMs like o3 can be incredibly effective persuaders *without* actually understanding your mental states. 🧵👇

1135

Reposted by Daniel Wurgaft

Michael Lepori @michael-lepori.bsky.social · 26/02/2026

🚨New preprint! In-context learning underlies LLMs’ real-world utility, but what are its limits? Can LLMs learn completely novel representations in-context and flexibly deploy them to solve tasks? In other words, can LLMs construct an in-context world model? Let’s see! 👀

1375

Reposted by Daniel Wurgaft

Eghbal Hosseini @eghbal-hosseini.bsky.social · 04/02/2026

How do diverse context structures reshape representations in LLMs? In our new work, we explore this via representational straightening. We found LLMs are like a Swiss Army knife: they select different computational mechanisms reflected in different representational structures. 1/

13911

Reposted by Daniel Wurgaft

Andrew Saxe @saxelab.bsky.social · 03/02/2026

Why don’t neural networks learn all at once, but instead progress from simple to complex solutions? And what does “simple” even mean across different neural network architectures? Sharing our new paper @iclr_conf led by Yedi Zhang with Peter Latham arxiv.org/abs/2512.20607

716042