Related papers: CaO$_2$: Rectifying Inconsistencies in Diffusion-B…
Diffusion distillation represents a highly promising direction for achieving faithful text-to-image generation in a few sampling steps. However, despite recent successes, existing distilled models still do not provide the full spectrum of…
Diffusion models have recently emerged as the dominant approach in visual generation tasks. However, the lengthy denoising chains and the computationally intensive noise estimation networks hinder their applicability in low-latency and…
Advanced change detection techniques primarily target image pairs of equal and high quality. However, variations in imaging conditions and platforms frequently lead to image pairs with distinct qualities: one image being high-quality, while…
Recent works in dataset distillation seek to minimize training expenses by generating a condensed synthetic dataset that encapsulates the information present in a larger real dataset. These approaches ultimately aim to attain test accuracy…
Dataset distillation compresses a large dataset into a small synthetic subset that retains essential information. Existing methods assume that all samples are perfectly labeled, limiting their real-world applications where incorrect labels…
Dataset Distillation aims to compress a large dataset into a small synthetic one while maintaining predictive performance. We show that as different demographic groups exhibit distinct predictive patterns, the distillation process struggles…
Diffusion models produce high-quality text-to-image results, but their iterative denoising is computationally expensive.Distribution Matching Distillation (DMD) emerges as a promising path to few-step distillation, but suffers from…
Recent approaches have shown promises distilling diffusion models into efficient one-step generators. Among them, Distribution Matching Distillation (DMD) produces one-step generators that match their teacher in distribution, without…
This study presents a novel approach to enhance the cost-to-quality ratio of image generation with diffusion models. We hypothesize that differences between distilled (e.g. FLUX.1-schnell) and baseline (e.g. FLUX.1-dev) models are…
What does a neural network learn when training from a task-specific dataset? Synthesizing this knowledge is the central idea behind Dataset Distillation, which recent work has shown can be used to compress large datasets into a small set of…
Accurately identifying student misconceptions is crucial for personalized education but faces three challenges: (1) data scarcity with long-tail distribution, where authentic student reasoning is difficult to synthesize; (2) fuzzy…
Dataset distillation aims to generate compact synthetic datasets that enable models trained on them to achieve performance comparable to those trained on full real datasets, while substantially reducing storage and computational costs.…
Diffusion-based text-to-image generation models trained on extensive text-image pairs have demonstrated the ability to produce photorealistic images aligned with textual descriptions. However, a significant limitation of these models is…
Dataset Distillation (DD) is a promising technique to synthesize a smaller dataset that preserves essential information from the original dataset. This synthetic dataset can serve as a substitute for the original large-scale one, and help…
Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…
While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains challenging, particularly in maintaining multi-view consistency. Classical approaches…
Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes, limiting practicality. Efforts such as progressive distillation or consistency distillation have shown promise by…
The aim of dataset distillation is to encode the rich features of an original dataset into a tiny dataset. It is a promising approach to accelerate neural network training and related studies. Different approaches have been proposed to…
Diffusion and flow matching models generate high-fidelity data by simulating paths defined by Ordinary or Stochastic Differential Equations (ODEs/SDEs), starting from a tractable prior distribution. The probability flow ODE formulation…
Diffusion models have made substantial advances in image generation, yet models trained on large, unfiltered datasets often yield outputs misaligned with human preferences. Numerous methods have been proposed to fine-tune pre-trained…