Daniel Wurgaft
@danielwurgaft
PhD @Stanford working w @noahdgoodman Studying in-context learning and reasoning in humans and machines Prev. @UofT CS & Psych
🚨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/
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/
Submit to our workshop on contextualizing Cogsci approaches for understanding neural networks---"Cognitive interpretability"!
We’re 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/
Check out my boy @dmkrash presenting our “outstanding paper award” winner at the Actionable Interpretability workshop today!
Check out my posters today if you're at ICML! 1) Detecting high-stakes interactions with activation probes — Outstanding paper @ Actionable interp workshop, 10:40-11:40 2) LLMs’ activations linearly encode training-order recency — Best paper runner up @ MemFM workshop, 2:30-3:45
Don't forget to tune in tomorrow, July 10th for a session with @EkdeepL on "Rational Analysis of In-Context Learning Elicits a Loss-Complexity Tradeoff" Learn more: cohere.com/events/Cohere-…
How do LLMs learn new tasks from just a few examples? What’s happening inside during in-context learning? 🤔 Join us July 10 for a talk by @EkdeepL on how LLMs adapt like cognitive maps—and how we can predict their behavior without accessing weights.
So proud! Go work with Gabriel, he’ll be the best advisor
Thrilled to join the UMich faculty in 2026! I'll also be recruiting PhD students this upcoming cycle. If you're interested in AI and formal reasoning, consider applying!
Thrilled to join the UMich faculty in 2026! I'll also be recruiting PhD students this upcoming cycle. If you're interested in AI and formal reasoning, consider applying!
We’re happy to announce that @GabrielPoesia will be joining our faculty as an assistant professor in Fall 2026. Welcome to CSE! ▶️Learn more about Gabriel here: gpoesia.com #UMichCSE #GoBlue
I’m recruiting PhD students to join the Computational Minds and Machines Lab at the University of Washington in Seattle! Join us to work at the intersection of computational cognitive science and AI with a broad focus on social intelligence. (Please reshare!)
Watch @EkdeepL talk about our recent paper explaining and predicting Transformer in-context learning behavior throughout training!
I'll be giving an online talk at Cohere Labs---join!
How do LLMs learn new tasks from just a few examples? What’s happening inside during in-context learning? 🤔 Join us July 10 for a talk by @EkdeepL on how LLMs adapt like cognitive maps—and how we can predict their behavior without accessing weights.
🚨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/
Bayesian models as the ultimate normative theories neural network as the ultimate task-performing models
It turns out that a lot of the most interesting behavior of LLMs can be explained without knowing anything about architecture or learning algorithms. Here we predict the rise (and fall) of in-context learning using hierarchical Bayesian methods.
It’s like chain-of-thought for humans!
Can we record and study human chains of thought? The think-aloud method, where participants voice their thoughts as they solve a task, offers a way! In our #CogSci2025 paper co-led with Ben Prystawski, we introduce a method to automate analysis of human reasoning traces! (1/8)🧵
It turns out that a lot of the most interesting behavior of LLMs can be explained without knowing anything about architecture or learning algorithms. Here we predict the rise (and fall) of in-context learning using hierarchical Bayesian methods.
🚨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/
[LG] In-Context Learning Strategies Emerge Rationally D Wurgaft, E S Lubana, C F Park, H Tanaka... [Stanford University & Harvard University] (2025) arxiv.org/abs/2506.17859
Amazing! I was wondering why there is no good curated dataset on humans playing game of 24. Here it is now :)
Can we record and study human chains of thought? The think-aloud method, where participants voice their thoughts as they solve a task, offers a way! In our #CogSci2025 paper co-led with Ben Prystawski, we introduce a method to automate analysis of human reasoning traces! (1/8)🧵