Search Results for author:
Found 7 papers, 4 papers with code
Your Diffusion Model is Secretly a Zero-Shot Classifier
Our generative approach to classification, which we call Diffusion Classifier, attains strong results on a variety of benchmarks and outperforms alternative methods of extracting knowledge from diffusion models.
Internet Explorer: Targeted Representation Learning on the Open Web
Modern vision models typically rely on fine-tuning general-purpose models pre-trained on large, static datasets.
Understanding Collapse in Non-Contrastive Siamese Representation Learning
We empirically analyze these non-contrastive methods and find that SimSiam is extraordinarily sensitive to dataset and model size.
Functional Regularization for Reinforcement Learning via Learned Fourier Features
We propose a simple architecture for deep reinforcement learning by embedding inputs into a learned Fourier basis and show that it improves the sample efficiency of both state-based and image-based RL.
Generalized Hindsight for Reinforcement Learning
Compared to standard relabeling techniques, Generalized Hindsight provides a substantially more efficient reuse of samples, which we empirically demonstrate on a suite of multi-task navigation and manipulation tasks.
Autoregressive Models: What Are They Good For?
Autoregressive (AR) models have become a popular tool for unsupervised learning, achieving state-of-the-art log likelihood estimates.
Sub-policy Adaptation for Hierarchical Reinforcement Learning
Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards.
