170 citations · 251 across the 13 of their papers we have counts for
14 papers
Characterizing Model Robustness via Natural Input Gradients
Adrián Rodríguez-Muñoz, Tongzhou Wang, Antonio Torralba
Adversarially robust models are locally smooth around each data sample so that small perturbations cannot drastically change model outputs. In modern systems, such smoothness is us…
Generalizing Dataset Distillation via Deep Generative Prior
George Cazenavette, Tongzhou Wang, Antonio Torralba +2
Dataset Distillation aims to distill an entire dataset's knowledge into a few synthetic images. The idea is to synthesize a small number of synthetic data points that, when given t…
Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning
Tongzhou Wang, Antonio Torralba, Phillip Isola +1
In goal-reaching reinforcement learning (RL), the optimal value function has a particular geometry, called quasimetric structure. This paper introduces Quasimetric Reinforcement Le…
Steerable Equivariant Representation Learning
Sangnie Bhardwaj, Willie McClinton, Tongzhou Wang +4
Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval, and object detection. Data augmentation…
Procedural Image Programs for Representation Learning
Manel Baradad, Chun-Fu Chen, Jonas Wulff +4
Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias. Existing wor…
Totems: Physical Objects for Verifying Visual Integrity
Jingwei Ma, Lucy Chai, Minyoung Huh +4
We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene. Totems…
Denoised MDPs: Learning World Models Better Than the World Itself
Tongzhou Wang, Simon S. Du, Antonio Torralba +3
The ability to separate signal from noise, and reason with clean abstractions, is critical to intelligence. With this ability, humans can efficiently perform real world tasks witho…
Dataset Distillation by Matching Training Trajectories
George Cazenavette, Tongzhou Wang, Antonio Torralba +2
Dataset distillation is the task of synthesizing a small dataset such that a model trained on the synthetic set will match the test accuracy of the model trained on the full datase…
Rewriting a Deep Generative Model
David Bau, Steven Liu, Tongzhou Wang +2
A deep generative model such as a GAN learns to model a rich set of semantic and physical rules about the target distribution, but up to now, it has been obscure how such rules are…
Diverse Image Generation via Self-Conditioned GANs
Steven Liu, Tongzhou Wang, David Bau +2
We introduce a simple but effective unsupervised method for generating realistic and diverse images. We train a class-conditional GAN model without using manually annotated class l…
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
Tongzhou Wang, Phillip Isola
Contrastive representation learning has been outstandingly successful in practice. In this work, we identify two key properties related to the contrastive loss: (1) alignment (clos…
Dataset Distillation
Tongzhou Wang, Jun-Yan Zhu, Antonio Torralba +1
Model distillation aims to distill the knowledge of a complex model into a simpler one. In this paper, we consider an alternative formulation called dataset distillation: we keep t…
Learning to Synthesize a 4D RGBD Light Field from a Single Image
Pratul P. Srinivasan, Tongzhou Wang, Ashwin Sreelal +2
We present a machine learning algorithm that takes as input a 2D RGB image and synthesizes a 4D RGBD light field (color and depth of the scene in each ray direction). For training,…
Meta-Learning MCMC Proposals
Tongzhou Wang, Yi Wu, David A. Moore +1
Effective implementations of sampling-based probabilistic inference often require manually constructed, model-specific proposals. Inspired by recent progresses in meta-learning for…