Diffusion probabilistic models (DPMs) have shown remarkable performance in high-
resolution image synthesis but their sampling efficiency is still to be desired due to the …

Diffusion models (DMs) are a type of potential generative models, which have achieved
better effects in many fields than traditional methods. DMs consist of two main processes …

Using backward error analysis, we compute implicit training biases in multitask and
continual learning settings for neural networks trained with stochastic gradient descent. In …

Recent breakthroughs and successful deployment of large language and vision models in a
constrained environment predominantly follow a two phase approach. First, large models …

Using backward error analysis, we compute implicit training biases in multitask and
continual learning settings for neural networks trained with stochastic gradient descent. In …