Dave Epstein
YOU?
Author Swipe
View article: Disentangled 3D Scene Generation with Layout Learning
Disentangled 3D Scene Generation with Layout Learning Open
We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretrained text-to-image model. Our key insight is that objects …
View article: Diffusion Self-Guidance for Controllable Image Generation
Diffusion Self-Guidance for Controllable Image Generation Open
Large-scale generative models are capable of producing high-quality images from detailed text descriptions. However, many aspects of an image are difficult or impossible to convey through text. We introduce self-guidance, a method that pro…
View article: BlobGAN: Spatially Disentangled Scene Representations
BlobGAN: Spatially Disentangled Scene Representations Open
We propose an unsupervised, mid-level representation for a generative model of scenes. The representation is mid-level in that it is neither per-pixel nor per-image; rather, scenes are modeled as a collection of spatial, depth-ordered "blo…
View article: Learning Temporal Dynamics from Cycles in Narrated Video
Learning Temporal Dynamics from Cycles in Narrated Video Open
Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal cycle consistency jointly in vision and langua…
View article: Globetrotter: Unsupervised Multilingual Translation from Visual Alignment
Globetrotter: Unsupervised Multilingual Translation from Visual Alignment Open
Machine translation in a multi-language scenario requires large-scale parallel corpora for every language pair. Unsupervised translation is challenging because there is no explicit connection between languages, and the existing methods hav…
View article: Learning Temporal Dynamics from Cycles in Narrated Video
Learning Temporal Dynamics from Cycles in Narrated Video Open
Learning to model how the world changes as time elapses has proven a challenging problem for the computer vision community. We propose a self-supervised solution to this problem using temporal cycle consistency jointly in vision and langua…
View article: Globetrotter: Connecting Languages by Connecting Images
Globetrotter: Connecting Languages by Connecting Images Open
Machine translation between many languages at once is highly challenging, since training with ground truth requires supervision between all language pairs, which is difficult to obtain. Our key insight is that, while languages may vary dra…
View article: Learning Goals from Failure
Learning Goals from Failure Open
We introduce a framework that predicts the goals behind observable human action in video. Motivated by evidence in developmental psychology, we leverage video of unintentional action to learn video representations of goals without direct s…
View article: Video Representations of Goals Emerge from Watching Failure.
Video Representations of Goals Emerge from Watching Failure. Open
We introduce a video representation learning framework that models the latent goals behind observable human action. Motivated by how children learn to reason about goals and intentions by experiencing failure, we leverage unconstrained vid…
View article: Oops! Predicting Unintentional Action in Video
Oops! Predicting Unintentional Action in Video Open
From just a short glance at a video, we can often tell whether a person's action is intentional or not. Can we train a model to recognize this? We introduce a dataset of in-the-wild videos of unintentional action, as well as a suite of tas…
View article: NEUZZ: Efficient Fuzzing with Neural Program Smoothing
NEUZZ: Efficient Fuzzing with Neural Program Smoothing Open
Fuzzing has become the de facto standard technique for finding software vulnerabilities. However, even state-of-the-art fuzzers are not very efficient at finding hard-to-trigger software bugs. Most popular fuzzers use evolutionary guidance…
View article: NEUZZ: Efficient Fuzzing with Neural Program Learning
NEUZZ: Efficient Fuzzing with Neural Program Learning Open
Fuzzing has become the de facto standard technique for finding software vulnerabilities. However, even state-of-the-art fuzzers are not very efficient at finding hard-to-trigger software bugs. Most popular fuzzers use evolutionary guidance…
View article: NEUZZ: Efficient Fuzzing with Neural Program Smoothing
NEUZZ: Efficient Fuzzing with Neural Program Smoothing Open
Fuzzing has become the de facto standard technique for finding software vulnerabilities. However, even state-of-the-art fuzzers are not very efficient at finding hard-to-trigger software bugs. Most popular fuzzers use evolutionary guidance…