… generative … generative model, ie, generating (sampling) according to the structure of learned
world density. In this paper, we propose Generative Neurosymbolic Machines, a generative …

… Together, we call such a program a neurosymbolic … Generative Models (SGM) that combines
neurosymbolic programs representing global structure with state-of-the-art deep generative …

… Current machine learning … generative models of concepts that capture rich compositional
and causal structure, while learning from raw data. We develop a generative neuro-symbolic (…

… In this invited talk, we describe an AI assistant that leverages neuro-symbolic machine learning
to … We employ deep generative models in the form of fine-tuned large language models to …

… -level structure to guide the generative process, and many such … Our generative model has
two parts:(i) one model to … data, and then learn a generative model based on the resulting …

… Neurosymbolic generative models have shown promise in various natural language
processing tasks, such as semantic parsing, language modeling, and machine translation, by …

… We present Drawing out of Distribution (DooD), a neuro-symbolic generative model of
stroke-based drawing that can learn such general-purpose representations. In contrast to prior …

… In contrast, state-of-the-art generative models from machine learning struggle with creative
imagination, producing samples that either closely mimic the training data or that exhibit …

… In particular, our contribution is a new differentiable neurosymbolic particle filter that … we
propose a novel solution that takes advantage of the neurosymbolic nature of a NeSy-MM. While …

… with external neuro-symbolic components. We illustrate a hybrid framework centered on
ACT-R, and we discuss the role of generative models in recent and future applications. …