Interestingly, we can even analyze the generated image sequences using traditional computer vision algorithms to see the specific trajectories models take during in-context physical simulation. Like chain-of-thought, these intermediate steps are often structured and interpretable.
13.11.2025 21:36 — 👍 1 🔁 0 💬 0 📌 0
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.
13.11.2025 21:36 — 👍 7 🔁 2 💬 1 📌 0
out now in Open Mind: "People Evaluate Agents Based on the Algorithms That Drive Their Behavior"
by Bigelow & me
Paper: direct.mit.edu/opmi/article...
OSF: osf.io/yzbrq/?view_...
15.09.2025 13:29 — 👍 40 🔁 9 💬 1 📌 0
Our latest on the cognitive science of LLMs! To be presented @CogSci2025 🎉
LLMs are increasingly involved in human collaborations. How do LLMs assign responsibility and reward to collaborators? Is it similar to how humans do it? 🤖🧑
📃 gershmanlab.com/pubs/XiangBi... (1/4)
24.07.2025 00:19 — 👍 39 🔁 9 💬 2 📌 1
Professor of Natural and Artificial Intelligence @Stanford. Safety and alignment @GoogleDeepMind.
Group Leader, CBS-NTT "Physics of Intelligence" Program at Harvard
website: https://sites.google.com/view/htanaka/home
PhD student @ Harvard || computational cognitive science, human decision making and reasoning
Postdoc at Harvard and MIT.
PhD @Stanford working w @noahdgoodman and research fellow @GoodfireAI
Studying in-context learning and reasoning in humans and machines
Prev. @UofT CS & Psych
PhD @stanfordnlp.bsky.social
Postdoc at CBS, Harvard University
(New around here)
Cognitive scientist studying how we see + think @ Johns Hopkins University. 🇨🇦
Lab: https://perception.jhu.edu/
Tea drinking assistant professor of cognitive psychology at Stanford.
https://cicl.stanford.edu
Professor, Department of Psychology and Center for Brain Science, Harvard University
https://gershmanlab.com/
Assistant Professor @ UChicago CS & DSI UChicao
Leading Conceptualization Lab http://conceptualization.ai
Minting new vocabulary to conceptualize generative models.
Associate Professor, Department of Psychology, Harvard University. Computation, cognition, development.
Psych PhD student @Harvard
Asst Prof at Johns Hopkins Cognitive Science • Director of the Group for Language and Intelligence (GLINT) ✨• Interested in all things language, cognition, and AI
jennhu.github.io
