🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Published in Science today, Wai Keen Vong reports a dream experiment: he trained a multi-modal AI model from scratch on a subset of one child's experiences, as captured by headcam video. Shows how grounded word learning is possible in natural settings, as discussed in his thread:

What can an AI model learn when given the data from just one child? A surprising answer comes from a groundbreaking study published in Science by CDS Research Scientist Wai Keen Vong (Wai Keen Vong) and CDS Assistant Professor Brenden Lake (Brenden Lake). nyudatascience.medium.com/what-can-ai-sy…

Love the science.org home page right now (this isn't the baby who participated in the current study, but in the next one :))

Excellent article on Wai Keen Vong 's new work in the Washington Post by carolyn johnson, with discussion from Josh Tenenbaum and Michael Tomasello. Indeed, the next q is how verbs, pronouns, and abstract words can be learned. How far will data-driven go? washingtonpost.com/science/2024/0…

My thoughts on the fascinating new study in Science science.org/doi/10.1126/sc… by Vong et al in the Financial Times. 1/2 ft.com/content/f67196…

In just a minute, Wai Keen Vong is being interviewed on NPR Science Friday, about training models through the eyes and ears of a child. listen in here: kunc.org Also, see the NPR link here: sciencefriday.com/segments/langu…

Linda Smith, one of the scientists I most admire, writes in Nature "News and Views" about Wai Keen Vong 's work. Linda's conjecture: "problems of data-greedy AI could be mitigated by determining and then exploiting the natural statistics of infant experience" nature.com/articles/d4158…

Fun (and science) with the family highlighted in today's NYT. Comments from some of my favorite scientists Griffiths Computational Cognitive Science Lab, Linda Smith, and Michael C. Frank whose study Luna is participating in. Thanks Oliver Whang for the great writing. nytimes.com/2024/04/30/sci…

How do we measure similarities and differences between how kids and models learn language? We introduce DevBench, a suite of multimodal developmental evaluations with corresponding human data from both children and adults. 🧵 1/ 📝: arxiv.org/abs/2406.10215

One inspiration for ARC-AGI solutions is the psychology how humans solve novel tasks. A new study by todd gureckis Brenden Lake Solim LeGris Wai Keen Vong @ NYU explores human performance on ARC, finding that 98.7% of the public tasks are solvable by at least 1 MTurker.

We have a new preprint led by Solim LeGris and Wai Keen Vong (w/ Brenden Lake ) looking at how people solve the Abstraction and Reasoning benchmark. arxiv.org/abs/2409.01374 ARC is one of the most challenging & long standing AGI benchmarks and the focus of a large $$ prize ARC Prize 🧵

Exciting episode! 🎙️ We chat with Dr. Wai Keen Vong (Wai Keen Vong), lead author of the Science paper where an artificial neural network mapped words to referents using a child's egocentric recordings. Plus, we dive into Wai's journey in science! share.fireside.fm/episode/R8yhKe…

New ARC-AGI paper ARC Prize w/ fantastic collaborators Wen-Ding Li @ ICLR'25 Keya Hu Zenna Tavares evanthebouncy Basis For few-shot learning: better to construct a symbolic hypothesis/program, or have a neural net do it all, ala in-context learning? cs.cornell.edu/~ellisk/docume…