相关论文: Training-Free Motion Customization for Distilled V…

Diffusion models have achieved remarkable generation quality, but they suffer from significant inference cost due to their reliance on multiple sequential denoising steps, motivating recent efforts to distill this inference process into a…

Algorithmic efficiency techniques such as distillation (\cite{hinton2015distillation}) are useful in improving model quality without increasing serving costs, provided a larger teacher model is available for a smaller student model to learn…

Recent advances in egocentric video understanding models are promising, but their heavy computational expense is a barrier for many real-world applications. To address this challenge, we propose EgoDistill, a distillation-based approach…

Deploying language models often requires navigating accuracy vs. performance trade-offs to meet latency constraints while preserving utility. Traditional model distillation reduces size but incurs substantial costs through training separate…

Self-supervised image encoders such as DINO have recently gained significant interest for learning robust visual features without labels. However, most SSL methods train on static images and miss the temporal cues inherent in videos. We…

One-step generators distilled from Masked Diffusion Models (MDMs) compress multiple sampling steps into a single forward pass, enabling efficient text and image synthesis. However, they suffer two key limitations: they inherit modeling bias…

Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this via post-training, they typically rely on a bidirectional…

We present an ultra-efficient post-training method for shortcutting large-scale pre-trained flow matching diffusion models into efficient few-step samplers, enabled by novel velocity field self-distillation. While shortcutting in flow…

Diverse human motion generation is an increasingly important task, having various applications in computer vision, human-computer interaction and animation. While text-to-motion synthesis using diffusion models has shown success in…

Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong results in the chunk-wise 4-step regime by distilling…

Diffusion models have seen rapid adoption in robotic imitation learning, enabling autonomous execution of complex dexterous tasks. However, action synthesis is often slow, requiring many steps of iterative denoising, limiting the extent to…

Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers via reducing both…

Video Frame Interpolation (VFI) aims to synthesize intermediate frames between existing frames to enhance visual smoothness and quality. Beyond the conventional methods based on the reconstruction loss, recent works have employed generative…

Video-based action recognition is one of the most popular topics in computer vision. With recent advances of selfsupervised video representation learning approaches, action recognition usually follows a two-stage training framework, i.e.,…

Feature distillation is an effective way to improve the performance for a smaller student model, which has fewer parameters and lower computation cost compared to the larger teacher model. Unfortunately, there is a common obstacle - the gap…

Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temporal modeling. Besides the training burden, the generated…

We propose a training-free and robust solution to offer camera movement control for off-the-shelf video diffusion models. Unlike previous work, our method does not require any supervised finetuning on camera-annotated datasets or…

Data-Free Knowledge Distillation (KD) allows knowledge transfer from a trained neural network (teacher) to a more compact one (student) in the absence of original training data. Existing works use a validation set to monitor the accuracy of…

Diffusion models have achieved remarkable success in generating high-resolution, realistic images across diverse natural distributions. However, their performance heavily relies on high-quality training data, making it challenging to learn…

Generating realistic animated videos from static images is an important area of research in computer vision. Methods based on physical simulation and motion prediction have achieved notable advances, but they are often limited to specific…