Related papers: Veda: Scalable Video Diffusion via Distilled Spars…
In visual generation, the quadratic complexity of attention mechanisms results in high memory and computational costs, especially for longer token sequences required in high-resolution image or multi-frame video generation. To address this,…
Large convolutional neural network models have recently demonstrated impressive performance on video attention prediction. Conventionally, these models are with intensive computation and large memory. To address these issues, we design an…
Diffusion Transformers (DiTs) can generate short photorealistic videos, yet directly training and sampling longer videos with full attention across the video remains computationally challenging. Alternative methods break long videos down…
Video Quality Assessment (VQA), which aims to predict the perceptual quality of a video, has attracted raising attention with the rapid development of streaming media technology, such as Facebook, TikTok, Kwai, and so on. Compared with…
Most of the existing works in supervised spatio-temporal video super-resolution (STVSR) heavily rely on a large-scale external dataset consisting of paired low-resolution low-frame rate (LR-LFR)and high-resolution high-frame-rate (HR-HFR)…
Diffusion Transformers dominate video generation, but the quadratic complexity of attention computation introduces substantial latency. Attention sparsity reduces computational costs by focusing on critical tokens while ignoring…
Advanced autoregressive (AR) video generation models have improved visual fidelity and interactivity, but the quadratic complexity of attention remains a primary bottleneck for efficient deployment. While existing sparse attention solutions…
Achieving ID-preserving text-to-video (T2V) generation remains challenging despite recent advances in diffusion-based models. Existing approaches often fail to capture fine-grained facial dynamics or maintain temporal identity coherence. To…
Diffusion based approaches to long form text generation suffer from prohibitive computational cost and memory overhead as sequence length increases. We introduce SA-DiffuSeq, a diffusion framework that integrates sparse attention to…
The quadratic time and memory complexity of the attention mechanism in modern Transformer based video generators makes end-to-end training for ultra high resolution videos prohibitively expensive. Motivated by this limitation, we introduce…
In recent years, the rapid expansion of dataset sizes and the increasing complexity of deep learning models have significantly escalated the demand for computational resources, both for data storage and model training. Dataset distillation…
We introduce Lavender, a simple supervised fine-tuning (SFT) method that boosts the performance of advanced vision-language models (VLMs) by leveraging state-of-the-art image generation models such as Stable Diffusion. Specifically,…
Video diffusion models have rapidly become the dominant paradigm for high-fidelity generative video synthesis, but their practical deployment remains constrained by severe inference costs. Compared with image generation, video synthesis…
Transformer-based video diffusion models rely on 3D attention over spatial and temporal tokens, which incurs quadratic time and memory complexity and makes end-to-end training for ultra-high-resolution videos prohibitively expensive. To…
Leveraging the diffusion transformer (DiT) architecture, models like Sora, CogVideoX and Wan have achieved remarkable progress in text-to-video, image-to-video, and video editing tasks. Despite these advances, diffusion-based video…
Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains…
Diffusion models have achieved remarkable success in generative tasks but suffer from high computational costs due to their iterative sampling process and quadratic attention costs. Existing training-free acceleration strategies that reduce…
Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…
The recent wave of AI-generated content has witnessed the great development and success of Text-to-Image (T2I) technologies. By contrast, Text-to-Video (T2V) still falls short of expectations though attracting increasing interests. Existing…
Diffusion models have demonstrated impressive performance in generating high-quality videos from text prompts or images. However, precise control over the video generation process, such as camera manipulation or content editing, remains a…