Related papers: Sortblock: Similarity-Aware Feature Reuse for Diff…

We present a supervised learning framework of training generative models for density estimation. Generative models, including generative adversarial networks, normalizing flows, variational auto-encoders, are usually considered as…

Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing caching methods…

Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce CoReDiT, a structured token pruning framework for DiTs across…

Imitation learning, particularly Diffusion Policies based methods, has recently gained significant traction in embodied AI as a powerful approach to action policy generation. These models efficiently generate action policies by learning to…

Diffusion Transformers (DiTs) achieve state-of-the-art results in text-to-image, text-to-video generation, and editing. However, their large model size and the quadratic cost of spatial-temporal attention over multiple denoising steps make…

Diffusion models have demonstrated remarkable capabilities in visual content generation but remain challenging to deploy due to their high computational cost during inference. This computational burden primarily arises from the quadratic…

Diffusion model deployment has been suffering from high energy consumption and inference latency despite its superior performance in visual generation tasks. Dynamic voltage and frequency scaling (DVFS) offers a promising solution to…

Diffusion Transformers (DiT) have become a leading architecture in image generation. However, the quadratic complexity of attention mechanisms, which are responsible for modeling token-wise relationships, results in significant latency when…

While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers…

Recently, Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation, surpassing U-Net-based models in terms of performance. However, the enhanced capabilities of DiTs come with significant drawbacks,…

Diffusion Transformers (DiTs) excel in generative tasks but face practical deployment challenges due to high inference costs. Feature caching, which stores and retrieves redundant computations, offers the potential for acceleration.…

Diffusion Transformer (DiT) has now become the preferred choice for building image generation models due to its great generation capability. Unlike previous convolution-based UNet models, DiT is purely composed of a stack of transformer…

Feature caching has emerged as an effective strategy to accelerate diffusion transformer (DiT) sampling through temporal feature reuse. It is a challenging problem since (1) Progressive error accumulation from cached blocks significantly…

Diffusion models have recently advanced Combinatorial Optimization (CO) as a powerful backbone for neural solvers. However, their iterative sampling process requiring denoising across multiple noise levels incurs substantial overhead. We…

Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the quadratic complexity in self-attention and the extensive…

Generating temporally-consistent high-fidelity videos can be computationally expensive, especially over longer temporal spans. More-recent Diffusion Transformers (DiTs) -- despite making significant headway in this context -- have only…

Diffusion models produce high quality images but inference is costly due to many denoising steps and heavy matrix operations. We present DiffPro, a post-training, hardware-faithful framework that works with the exact integer kernels used in…

Action diffusion excels at high-fidelity action generation but incurs heavy computational costs owing to its iterative denoising nature. Despite current technologies showing promise in accelerating diffusion transformers by reusing the…

Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an…

One of the main drawback of diffusion models is the slow inference time for image generation. Among the most successful approaches to addressing this problem are distillation methods. However, these methods require considerable…