Related papers: TaoCache: Structure-Maintained Video Generation Ac…

High-density biosignal recordings are critical for neural decoding and clinical monitoring, yet real-world deployments often rely on low-density (LD) montages due to hardware and operational constraints. This motivates spatial…

Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in…

Interactive long video generation requires prompt switching to introduce new subjects or events, while maintaining perceptual fidelity and coherent motion over extended horizons. Recent distilled streaming video diffusion models reuse a…

With the revolution of generative AI, video-related tasks have been widely studied. However, current state-of-the-art video models still lag behind image models in visual quality and user control over generated content. In this paper, we…

Diffusion Transformers (DiTs) achieve strong visual quality, but their iterative denoising process requires many costly Transformer evaluations. Training-free acceleration methods reduce this cost by caching, forecasting, or verifying…

Reconstructing 3D scenes and synthesizing novel views from sparse input views is a highly challenging task. Recent advances in video diffusion models have demonstrated strong temporal reasoning capabilities, making them a promising tool for…

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…

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…

This paper presents the Neural Cache architecture, which re-purposes cache structures to transform them into massively parallel compute units capable of running inferences for Deep Neural Networks. Techniques to do in-situ arithmetic in…

Diffusion-based image generation models excel at producing high-quality synthetic content, but suffer from slow and computationally expensive inference. Prior work has attempted to mitigate this by caching and reusing features within…

We propose in this paper an analytically new construct of a diffusion model whose drift and diffusion parameters yield an exponentially time-decaying Signal to Noise Ratio in the forward process. In reverse, the construct cleverly carries…

With the availability of large-scale video datasets and the advances of diffusion models, text-driven video generation has achieved substantial progress. However, existing video generation models are typically trained on a limited number of…

Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive…

Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models. Block diffusion improves inference efficiency via KV caching and block-wise causal inference and has been…

Video generation based on diffusion models presents a challenging multimodal task, with video editing emerging as a pivotal direction in this field. Recent video editing approaches primarily fall into two categories: training-required and…

Sparse neural networks are becoming increasingly important as the field seeks to improve the performance of existing models by scaling them up, while simultaneously trying to reduce power consumption and computational footprint.…

Reducing token count is crucial for efficient training and inference of latent diffusion models, especially at high resolution. A common strategy is to build high-compression image tokenizers with more channels per token. However, when…

Generating videos of complex human motions such as flips, cartwheels, and martial arts remains challenging for current video diffusion models. Text-only conditioning is temporally ambiguous for fine-grained motion control, while explicit…

The field of video generation has expanded significantly in recent years, with controllable and compositional video generation garnering considerable interest. Most methods rely on leveraging annotations such as text, objects' bounding…

Recent studies have demonstrated that the forward diffusion process is crucial for the effectiveness of diffusion models in terms of generative quality and sampling efficiency. We propose incorporating an analytical image attenuation…