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.
Modern vision models typically rely on fine-tuning general-purpose models pre-trained on large, static datasets.
We empirically analyze these non-contrastive methods and find that SimSiam is extraordinarily sensitive to dataset and model size.
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.
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.
Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards.