Results 301 - 310 of 24333
John is currently a PhD student at Columbia university, studying theoretical computer science with a focus on quantum computing.
This workshop is about the closely related subjects of random graphs, random manifolds, and random matrices. Random graph theory and random matrix theory have various applications in theoretical computer science. Recently there are major new developments...
We introduce a novel, high-capacity associative memory capable of factorizing compositional representations of the world. The approach is implemented as a continuous-time oscillator neural network. By performing factorization with a continuous-time dynamical system, the network provides efficient solutions to computationally hard problems such as perceptual inference world variables such as form and motion, or combinatorial optimization problems such as subset sum. We demonstrate favorable performance compared to existing approaches to factorization, efficient implementation, and relevance to standard tasks such as the subset sum problem. We also identify concrete reasons why our model exhibits improved capacity, by formulating methods to track its convergence.
Humans navigate complex social environments by continuously predicting the behavior, intentions, and beliefs of others. Inspired by this ability, Social World Models extend existing physical world models to the social domain, capturing not only physical dynamics but also the latent mental states and strategies of interacting agents. This talk will explore how these models can be learned, represented, and leveraged to build towards socially intelligent AI. We will present our recent work in multimodal modeling of social behaviors, social reasoning benchmarks and models, and long-horizon self-evolving social agents.
I will present results of the memory study of human recall of meaningful narratives. Analysis of recalls indicate the hierarchical nature of narrative representation in memory resulting from prior comprehension. A mathematical model of hierarchical recall reproduces the results and points to hierarchical nature of language itself. LLM-assisted semantic segmentation of texts provides a further evidence fo these conclusions.