Related papers: LeMiCa: Lexicographic Minimax Path Caching for Eff…

Prior masked modeling motion generation methods predominantly study text-to-motion. We present DiMo, a discrete diffusion-style framework, which extends masked modeling to bidirectional text--motion understanding and generation. Unlike…

Diffusion Transformers are fundamental for video and image generation, but their efficiency is bottlenecked by the quadratic complexity of attention. While block sparse attention accelerates computation by attending only critical key-value…

Diffusion models have emerged as state-of-the-art in image generation, but their practical deployment is hindered by the significant computational cost of their iterative denoising process. While existing caching techniques can accelerate…

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy…

Diffusion-based generative models have become dominant generators of high-fidelity images and videos but remain limited by their computationally expensive inference procedures. Existing acceleration techniques either require extensive model…

Text-driven image and video diffusion models have recently achieved unprecedented generation realism. While diffusion models have been successfully applied for image editing, very few works have done so for video editing. We present the…

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…

A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data…

Masked Diffusion Models (MDMs) offer a promising alternative to autoregressive language models by enabling parallel token generation and bidirectional context modeling. However, their inference speed is significantly limited by the…

Protein sequence design has seen significant advances through discrete diffusion and autoregressive approaches, yet the potential of continuous diffusion remains underexplored. Here, we present DiMA, a latent diffusion framework that…

Long video generation remains a challenging and compelling topic in computer vision. Diffusion based models, among the various approaches to video generation, have achieved state of the art quality with their iterative denoising procedures.…

The tremendous progress in neural image generation, coupled with the emergence of seemingly omnipotent vision-language models has finally enabled text-based interfaces for creating and editing images. Handling generic images requires a…

Recent advances in diffusion models have demonstrated remarkable capabilities in video generation. However, the computational intensity remains a significant challenge for practical applications. While feature caching has been proposed to…

Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency challenges. In this paper, we exploit the inherent temporal…

Creating high-fidelity, coherent long videos is a sought-after aspiration. While recent video diffusion models have shown promising potential, they still grapple with spatiotemporal inconsistencies and high computational resource demands.…

Diffusion-based language models (dLLMs) have emerged as a promising alternative to traditional autoregressive LLMs by enabling parallel token generation and significantly reducing inference latency. However, existing sampling strategies for…

Efficient streaming video generation is critical for simulating interactive and dynamic worlds. Existing methods distill few-step video diffusion models with sliding window attention, using initial frames as sink tokens to maintain…

3D Gaussian Splatting (3DGS) enhances 3D scene reconstruction through explicit representation and fast rendering, demonstrating potential benefits for various low-level vision tasks, including video compression. However, existing 3DGS-based…

Image diffusion models are trained on independently sampled static images. While this is the bedrock task protocol in generative modeling, capturing the temporal world through the lens of static snapshots is information-deficient by design.…

Text-driven human motion generation based on diffusion strategies establishes a reliable foundation for multimodal applications in human-computer interactions. However, existing advances face significant efficiency challenges due to the…