Related papers: Churn Reduction via Distillation
Consistency models imitate the multi-step sampling of score-based diffusion in a single forward pass of a neural network. They can be learned in two ways: consistency distillation and consistency training. The former relies on the true…
Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input $x$ and any target classification $t$, it is possible to find a new…
Dataset distillation aims to minimize the time and memory needed for training deep networks on large datasets, by creating a small set of synthetic images that has a similar generalization performance to that of the full dataset. However,…
Knowledge distillation is one of the most popular and effective techniques for knowledge transfer, model compression and semi-supervised learning. Most existing distillation approaches require the access to original or augmented training…
Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…
Diffusion Models~(DMs) have emerged as the dominant approach in Generative Artificial Intelligence (GenAI), owing to their remarkable performance in tasks such as text-to-image synthesis. However, practical DMs, such as stable diffusion,…
Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the large model and retains the performance close to that of the…
In the zero-shot policy transfer setting in reinforcement learning, the goal is to train an agent on a fixed set of training environments so that it can generalise to similar, but unseen, testing environments. Previous work has shown that…
In recent years, online distillation has emerged as a powerful technique for adapting real-time deep neural networks on the fly using a slow, but accurate teacher model. However, a major challenge in online distillation is catastrophic…
We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teacher network can learn…
In many practical scenarios -- like hyperparameter search or continual retraining with new data -- related training runs are performed many times in sequence. Current practice is to train each of these models independently from scratch. We…
Despite the popularity and efficacy of knowledge distillation, there is limited understanding of why it helps. In order to study the generalization behavior of a distilled student, we propose a new theoretical framework that leverages…
Current LLM unlearning methods are not robust. A few steps of finetuning can revert their effects. We begin by showing that this is true even for an idealized form of unlearning: training to imitate a model that was never trained on…
In this work, we show that it is possible to extract significant amounts of alignment training data from a post-trained model -- useful to steer the model to improve certain capabilities such as long-context reasoning, safety, instruction…
Distillation transfers knowledge from a large model trained on broad data to a smaller, more efficient model suitable for deployment. In structured prediction settings, prior knowledge about the task can guide the choice of a target…
End-to-end training with back propagation is the standard method for training deep neural networks. However, as networks become deeper and bigger, end-to-end training becomes more challenging: highly non-convex models gets stuck easily in…
Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised…
Modern neural networks do not always produce well-calibrated predictions, even when trained with a proper scoring function such as cross-entropy. In classification settings, simple methods such as isotonic regression or temperature scaling…
We propose an efficient way to output better calibrated uncertainty scores from neural networks. The Distilled Dropout Network (DDN) makes standard (non-Bayesian) neural networks more introspective by adding a new training loss which…
Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…