Related papers: Catch-Up Distillation: You Only Need to Train Once…

Recently, diffusion models have achieved significant advances in vision, text, and robotics. However, they still face slow generation speeds due to sequential denoising processes. To address this, a parallel sampling method based on Picard…

We introduce the problem of continual distillation learning (CDL) in order to use knowledge distillation (KD) to improve prompt-based continual learning (CL) models. The CDL problem is valuable to study since the use of a larger vision…

Dataset Distillation (DD) seeks to create a condensed dataset that, when used to train a model, enables the model to achieve performance similar to that of a model trained on the entire original dataset. It relieves the model training from…

The knowledge distillation uses a high-performance teacher network to guide the student network. However, the performance gap between the teacher and student networks can affect the student's training. This paper proposes a novel knowledge…

Consistency distillation is a prevalent way for accelerating diffusion models adopted in consistency (trajectory) models, in which a student model is trained to traverse backward on the probability flow (PF) ordinary differential equation…

Dataset distillation compresses large datasets into compact synthetic sets with comparable performance in training models. Despite recent progress on diffusion-based distillation, this type of method typically depends on heuristic guidance…

Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style video distillation faces two coupled challenges: the fake score must track a continuously…

Hand-crafting high quality prompts to optimize the performance of language models is a complicated and labor-intensive process. Furthermore, when migrating to newer, smaller, or weaker models (possibly due to latency or cost gains), prompts…

Efficiency and trustworthiness are two eternal pursuits when applying deep learning in real-world applications. With regard to efficiency, dataset distillation (DD) endeavors to reduce training costs by distilling the large dataset into a…

Diffusion distillation methods aim to compress the diffusion models into efficient one-step generators while trying to preserve quality. Among them, Distribution Matching Distillation (DMD) offers a suitable framework for training…

Diffusion model distillation has emerged as a powerful technique for creating efficient few-step and single-step generators. Among these, Distribution Matching Distillation (DMD) and its variants stand out for their impressive performance,…

Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize…

Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the generalization and robustness of the trained model. Knowledge distillation (KD), on the…

On-policy distillation (OPD) is an increasingly important paradigm for post-training language models. However, we identify a pervasive Scaling Law of Miscalibration: while OPD effectively improves task accuracy, it systematically traps…

Knowledge Distillation (KD) has emerged as a prominent technique for model compression. However, conventional KD approaches primarily focus on homogeneous architectures with identical tokenizers, constraining their applicability in…

Knowledge distillation(KD) aims to improve the performance of a student network by mimicing the knowledge from a powerful teacher network. Existing methods focus on studying what knowledge should be transferred and treat all samples equally…

Real-world object detection models should be cheap and accurate. Knowledge distillation (KD) can boost the accuracy of a small, cheap detection model by leveraging useful information from a larger teacher model. However, a key challenge is…

Knowledge distillation is an effective way to transfer knowledge from a strong teacher to an efficient student model. Ideally, we expect the better the teacher is, the better the student. However, this expectation does not always come true.…

We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In contrast to previous approaches that relied on smaller amateur…

In continual learning, there is a serious problem of catastrophic forgetting, in which previous knowledge is forgotten when a model learns new tasks. Various methods have been proposed to solve this problem. Replay methods which replay data…