Contemporary neural networks still fall short of human-level generalization, which extends
far beyond our direct experiences. In this paper, we argue that the underlying cause for this …

Zero-shot 3D shape understanding aims to recognize “unseen” 3D categories that are not
present in training data. Recently, Contrastive Language–Image Pre-training (CLIP) has …

The original" Seven Motifs" set forth a roadmap of essential methods for the field of scientific
computing, where a motif is an algorithmic method that captures a pattern of computation …

Generative latent-variable models are emerging as promising tools in robotics and
reinforcement learning. Yet, even though tasks in these domains typically involve distinct …

We present a fast inverse-graphics framework for instance-level 3D scene understanding.
We train a deep convolutional network that learns to map image regions to the full 3D shape …

How can one perform Bayesian inference on stochastic simulators with intractable
likelihoods? A recent approach is to learn the posterior from adaptively proposed …

Abstract We present Sequential Neural Likelihood (SNL), a new method for Bayesian
inference in simulator models, where the likelihood is intractable but simulating data from …

We present ObSuRF, a method which turns a single image of a scene into a 3D model
represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to …

We present a neural architecture that takes as input a 2D or 3D shape and outputs a
program that generates the shape. The instructions in our program are based on …

We present 3DP3, a framework for inverse graphics that uses inference in a structured
generative model of objects, scenes, and images. 3DP3 uses (i) voxel models to represent …