🔥 The program for the NLRSE workshop at #ACL2023NLP is posted 🔥 nl-reasoning-workshop.github.io In addition to the 5 invited talks, we have a fantastic technical program with 70 papers being presented! Make sure you stick around on Thursday after the main conference!

Cognitive scientists! You don’t want to miss our #CogSci2023 Workshop: “How does the mind discover useful abstractions?” cogsci-abstractions-workshop.github.io Co-organized w/ the peerless Wai Keen Vong + Lio Wong + Marcelo Mattar!

🔥Preprint Alert🔥 Excited to share some new work modeling human 3D shape perception! “Approaching human 3D shape perception with neurally mappable models” w/ tyler bonnen, @_yonifriedman, Ayush Tewari, Josh Tenenbaum, Vincent Sitzmann, Nancy Kanwisher @[email protected] arxiv.org/abs/2308.11300 🧵

📢 Introducing 🔗LINC, a neurosymbolic approach to logical reasoning w/ awesome co-first authors Theo X. Olausson, Ben Lipkin, and Cedegao Zhang + advisors Armando Solar-Lezama, Josh Tenenbaum, and Roger Levy! 📜arxiv.org/abs/2310.15164 💻github.com/benlipkin/linc 🧵⬇️ (1/n)

What if we equipped LLMs with cutting-edge code refactoring tools? 🤖🛠 Presenting LILO: Library Induction with Language Observations 📝 arxiv.org/abs/2310.19791 💻 github.com/gabegrand/lilo + Lio Wong, Maddy Bowers, Theo X. Olausson, Muxin Liu, Josh Tenenbaum & Jacob Andreas️ 🧵⬇️

Once upon a time, a mighty sphinx, the Area Chair of Thebes, terrorized all who dared to cross the mountain path into the city. Travelers would be asked the riddle: “How is a photon like a rational agent?” Failure to answer resulted in an immediate desk reject. #NeurIPS2023

There have been tremendous advances at the nexus of AI + mathematics. But it’s worth reflecting what our goals are for automated mathematicians. In our brief position piece for the #MathAI workshop NeurIPS Conference, we argue now is a great time to look to CogSci for reflection! 1/

[publication] "Perception of 3D shape integrates intuitive physics and analysis-by-synthesis" Research from CoCoSci MIT studying intuitive physics to explain how shape can be inferred from the deformations it causes to other objects, as in cloth draping. cbmm.mit.edu/publications/p…

In a seminal paper by Brenden Lake @ CogSci Tomer Ullman CoCoSci MIT and Sam Gershman put forward core domains of intelligence that are easy for people to reason about but difficult for machines. These include intuitive physics, causal reasoning, and intuitive psychology, among others.

I'm deeply honored to receive one of this year's CogSci Society Glushko Dissertation Prizes. While I'm still in a state of disbelief about the award, what I can say in no uncertain terms, is that developing these ideas with Rebecca Saxe has been immensely formative and rewarding.

Ready to unlock new insights? Join this upcoming workshop and let's learn together!

Tomorrow, Oct. 8, François Chollet Mike Knoop are bringing ARC Prize live to Massachusetts Institute of Technology (MIT) in Boston! Thanks to Prof. Josh Tenenbaum, MIT Brain and Cognitive Sciences, CoCoSci MIT, and AI@MIT for making this event possible. MIT students & staff - register now to get in! lu.ma/579tcudx

How do people reason while still staying coherent – as if they have an internal ‘world model’ for situations they’ve never encountered? A new paper on open-world cognition (preview at the world models workshop at #ICML2025!)

How do people reason so flexibly about new problems, bringing to bear globally-relevant knowledge while staying locally-consistent? Can we engineer a system that can synthesize bespoke world models (expressed as probabilistic programs) on-the-fly?