Daniel Wurgaft
@danielwurgaft.bsky.social
PhD @Stanford working w @noahdgoodman and research fellow @GoodfireAI
Studying in-context learning and reasoning in humans and machines
Prev. @UofT CS & Psych
Studying in-context learning and reasoning in humans and machines
Prev. @UofT CS & Psych
Pinned
Daniel Wurgaft
@danielwurgaft.bsky.social
· Jun 28
🚨New paper! We know models learn distinct in-context learning strategies, but *why*? Why generalize instead of memorize to lower loss? And why is generalization transient?
Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵
1/
Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵
1/
Reposted by Daniel Wurgaft
Humans and LLMs think fast and slow. Do SAEs recover slow concepts in LLMs? Not really.
Our Temporal Feature Analyzer discovers contextual features in LLMs, that detect event boundaries, parse complex grammar, and represent ICL patterns.
Our Temporal Feature Analyzer discovers contextual features in LLMs, that detect event boundaries, parse complex grammar, and represent ICL patterns.
November 13, 2025 at 10:32 PM
Humans and LLMs think fast and slow. Do SAEs recover slow concepts in LLMs? Not really.
Our Temporal Feature Analyzer discovers contextual features in LLMs, that detect event boundaries, parse complex grammar, and represent ICL patterns.
Our Temporal Feature Analyzer discovers contextual features in LLMs, that detect event boundaries, parse complex grammar, and represent ICL patterns.
Reposted by Daniel Wurgaft
Excited to have this out! This was a fun project that started with YingQiao and I discussing whether VLMs can do mental simulation of physics like people do, and it culminated in a new method where we prompted image generation models to simulate a series of images frame-by-frame.
new pre-print,
"Chain of Time: In-Context Physical Simulation with Image Generation Models"
(by Wang, Bigelow, Li, and me)
arxiv.org/abs/2511.00110
"Chain of Time: In-Context Physical Simulation with Image Generation Models"
(by Wang, Bigelow, Li, and me)
arxiv.org/abs/2511.00110
November 13, 2025 at 9:36 PM
Excited to have this out! This was a fun project that started with YingQiao and I discussing whether VLMs can do mental simulation of physics like people do, and it culminated in a new method where we prompted image generation models to simulate a series of images frame-by-frame.
Reposted by Daniel Wurgaft
🚨 NEW PREPRINT: Multimodal inference through mental simulation.
We examine how people figure out what happened by combining visual and auditory evidence through mental simulation.
Paper: osf.io/preprints/ps...
Code: github.com/cicl-stanfor...
We examine how people figure out what happened by combining visual and auditory evidence through mental simulation.
Paper: osf.io/preprints/ps...
Code: github.com/cicl-stanfor...
September 16, 2025 at 7:04 PM
🚨 NEW PREPRINT: Multimodal inference through mental simulation.
We examine how people figure out what happened by combining visual and auditory evidence through mental simulation.
Paper: osf.io/preprints/ps...
Code: github.com/cicl-stanfor...
We examine how people figure out what happened by combining visual and auditory evidence through mental simulation.
Paper: osf.io/preprints/ps...
Code: github.com/cicl-stanfor...
Reposted by Daniel Wurgaft
🚨New paper out w/ @gershbrain.bsky.social & @fierycushman.bsky.social from my time @Harvard!
Humans are capable of sophisticated theory of mind, but when do we use it?
We formalize & document a new cognitive shortcut: belief neglect — inferring others' preferences, as if their beliefs are correct🧵
Humans are capable of sophisticated theory of mind, but when do we use it?
We formalize & document a new cognitive shortcut: belief neglect — inferring others' preferences, as if their beliefs are correct🧵
September 17, 2025 at 12:58 AM
🚨New paper out w/ @gershbrain.bsky.social & @fierycushman.bsky.social from my time @Harvard!
Humans are capable of sophisticated theory of mind, but when do we use it?
We formalize & document a new cognitive shortcut: belief neglect — inferring others' preferences, as if their beliefs are correct🧵
Humans are capable of sophisticated theory of mind, but when do we use it?
We formalize & document a new cognitive shortcut: belief neglect — inferring others' preferences, as if their beliefs are correct🧵
Reposted by Daniel Wurgaft
*Sharing for our department’s trainees*
🧠 Looking for insight on applying to PhD programs in psychology?
✨ Apply by Sep 25th to Stanford Psychology's 9th annual Paths to a Psychology PhD info-session/workshop to have all of your questions answered!
📝 Application: tinyurl.com/pathstophd2025
🧠 Looking for insight on applying to PhD programs in psychology?
✨ Apply by Sep 25th to Stanford Psychology's 9th annual Paths to a Psychology PhD info-session/workshop to have all of your questions answered!
📝 Application: tinyurl.com/pathstophd2025
September 2, 2025 at 8:01 PM
*Sharing for our department’s trainees*
🧠 Looking for insight on applying to PhD programs in psychology?
✨ Apply by Sep 25th to Stanford Psychology's 9th annual Paths to a Psychology PhD info-session/workshop to have all of your questions answered!
📝 Application: tinyurl.com/pathstophd2025
🧠 Looking for insight on applying to PhD programs in psychology?
✨ Apply by Sep 25th to Stanford Psychology's 9th annual Paths to a Psychology PhD info-session/workshop to have all of your questions answered!
📝 Application: tinyurl.com/pathstophd2025
Reposted by Daniel Wurgaft
In neuroscience, we often try to understand systems by analyzing their representations — using tools like regression or RSA. But are these analyses biased towards discovering a subset of what a system represents? If you're interested in this question, check out our new commentary! Thread:
![What do representations tell us about a system? Image of a mouse with a scope showing a vector of activity patterns, and a neural network with a vector of unit activity patterns
Common analyses of neural representations: Encoding models (relating activity to task features) drawing of an arrow from a trace saying [on_____on____] to a neuron and spike train. Comparing models via neural predictivity: comparing two neural networks by their R^2 to mouse brain activity. RSA: assessing brain-brain or model-brain correspondence using representational dissimilarity matrices](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:e6ewzleebkdi2y2bxhjxoknt/bafkreiav2io2ska33o4kizf57co5bboqyyfdpnozo2gxsicrfr5l7qzjcq@jpeg)
August 5, 2025 at 2:36 PM
In neuroscience, we often try to understand systems by analyzing their representations — using tools like regression or RSA. But are these analyses biased towards discovering a subset of what a system represents? If you're interested in this question, check out our new commentary! Thread:
Reposted by Daniel Wurgaft
Super excited to have the #InfoCog workshop this year at #CogSci2025! Join us in SF for an exciting lineup of speakers and panelists, and check out the workshop's website for more info and detailed scheduled
sites.google.com/view/infocog...
sites.google.com/view/infocog...
July 22, 2025 at 7:18 PM
Super excited to have the #InfoCog workshop this year at #CogSci2025! Join us in SF for an exciting lineup of speakers and panelists, and check out the workshop's website for more info and detailed scheduled
sites.google.com/view/infocog...
sites.google.com/view/infocog...
Reposted by Daniel Wurgaft
Submit your latest and greatest papers to the hottest workshop on the block---on cognitive interpretability! 🔥
Excited to announce the first workshop on CogInterp: Interpreting Cognition in Deep Learning Models @ NeurIPS 2025! 📣
How can we interpret the algorithms and representations underlying complex behavior in deep learning models?
🌐 coginterp.github.io/neurips2025/
1/4
How can we interpret the algorithms and representations underlying complex behavior in deep learning models?
🌐 coginterp.github.io/neurips2025/
1/4
Home
First Workshop on Interpreting Cognition in Deep Learning Models (NeurIPS 2025)
coginterp.github.io
July 16, 2025 at 2:12 PM
Submit your latest and greatest papers to the hottest workshop on the block---on cognitive interpretability! 🔥
Reposted by Daniel Wurgaft
Excited to announce the first workshop on CogInterp: Interpreting Cognition in Deep Learning Models @ NeurIPS 2025! 📣
How can we interpret the algorithms and representations underlying complex behavior in deep learning models?
🌐 coginterp.github.io/neurips2025/
1/4
How can we interpret the algorithms and representations underlying complex behavior in deep learning models?
🌐 coginterp.github.io/neurips2025/
1/4
Home
First Workshop on Interpreting Cognition in Deep Learning Models (NeurIPS 2025)
coginterp.github.io
July 16, 2025 at 1:08 PM
Excited to announce the first workshop on CogInterp: Interpreting Cognition in Deep Learning Models @ NeurIPS 2025! 📣
How can we interpret the algorithms and representations underlying complex behavior in deep learning models?
🌐 coginterp.github.io/neurips2025/
1/4
How can we interpret the algorithms and representations underlying complex behavior in deep learning models?
🌐 coginterp.github.io/neurips2025/
1/4
Reposted by Daniel Wurgaft
A bias for simplicity by itself does not guarantee good generalization (see the No Free Lunch Theorems). So an inductive bias is only good to the extent that it reflects structure in the data. Is the world simple? The success of deep nets (with their intrinsic Occam's razor) would suggest yes(?)
July 8, 2025 at 1:57 PM
A bias for simplicity by itself does not guarantee good generalization (see the No Free Lunch Theorems). So an inductive bias is only good to the extent that it reflects structure in the data. Is the world simple? The success of deep nets (with their intrinsic Occam's razor) would suggest yes(?)
Reposted by Daniel Wurgaft
Really nice analysis!
🚨New paper! We know models learn distinct in-context learning strategies, but *why*? Why generalize instead of memorize to lower loss? And why is generalization transient?
Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵
1/
Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵
1/
June 28, 2025 at 8:03 AM
Really nice analysis!
🚨New paper! We know models learn distinct in-context learning strategies, but *why*? Why generalize instead of memorize to lower loss? And why is generalization transient?
Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵
1/
Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵
1/
June 28, 2025 at 2:35 AM
🚨New paper! We know models learn distinct in-context learning strategies, but *why*? Why generalize instead of memorize to lower loss? And why is generalization transient?
Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵
1/
Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵
1/
Excited to share a new CogSci paper co-led with @benpry.bsky.social!
Once a cornerstone for studying human reasoning, the think-aloud method declined in popularity as manual coding limited its scale. We introduce a method to automate analysis of verbal reports and scale think-aloud studies. (1/8)🧵
Once a cornerstone for studying human reasoning, the think-aloud method declined in popularity as manual coding limited its scale. We introduce a method to automate analysis of verbal reports and scale think-aloud studies. (1/8)🧵
June 25, 2025 at 5:00 AM
Excited to share a new CogSci paper co-led with @benpry.bsky.social!
Once a cornerstone for studying human reasoning, the think-aloud method declined in popularity as manual coding limited its scale. We introduce a method to automate analysis of verbal reports and scale think-aloud studies. (1/8)🧵
Once a cornerstone for studying human reasoning, the think-aloud method declined in popularity as manual coding limited its scale. We introduce a method to automate analysis of verbal reports and scale think-aloud studies. (1/8)🧵