Related papers: Attention-Driven Training-Free Efficiency Enhancem…
Despite the remarkable generation capabilities of Diffusion Models (DMs), conducting training and inference remains computationally expensive. Previous works have been devoted to accelerating diffusion sampling, but achieving data-efficient…
Latent Diffusion Models (LDMs) have emerged as powerful generative models, known for delivering remarkable results under constrained computational resources. However, deploying LDMs on resource-limited devices remains a complex issue,…
This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of denoising diffusion steps. In response to this observation,…
Diffusion models have demonstrated remarkable efficacy in various generative tasks with the predictive prowess of denoising model. Currently, diffusion models employ a uniform denoising model across all timesteps. However, the inherent…
Transformer-based Diffusion Probabilistic Models (DPMs) have shown more potential than CNN-based DPMs, yet their extensive computational requirements hinder widespread practical applications. To reduce the computation budget of…
Diffusion models currently dominate the field of data-driven image synthesis with their unparalleled scaling to large datasets. In this paper, we identify and rectify several causes for uneven and ineffective training in the popular ADM…
Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive capability of these models, however, often entails…
In recent advancements in high-fidelity image generation, Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a key player. However, their application at high resolutions presents significant computational challenges. Current…
Diffusion models have revolutionized generative tasks, especially in the domain of text-to-image synthesis; however, their iterative denoising process demands substantial computational resources. In this paper, we present a novel…
Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequently, methods for efficient finetuning, inference and…
Diffusion transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality. However, their computational cost remains a major bottleneck-attention alone accounts for over…
Video generation, while capable of generating realistic videos, is computationally expensive and slow, prohibiting real-time applications. In this paper, we observe that video latents encoded via an autoencoder under the Latent Diffusion…
Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for real-world applications is constrained by substantial computational costs and latency issues.…
Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…
Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a powerful family of generative models that can yield high-fidelity samples and competitive log-likelihoods across a range of domains, including image and speech synthesis.…
Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either before the LLM, limiting generality due to diverse…
Diffusion models achieve state-of-the-art image generation but remain computationally costly due to iterative denoising. Latent-space models like Stable Diffusion reduce overhead yet lose fine detail, while retrieval-augmented 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…
Diffusion models have achieved impressive advancements in various vision tasks. However, these gains often rely on increasing model size, which escalates computational complexity and memory demands, complicating deployment, raising…
Auto-regressive models (ARMs) have established a dominant paradigm in language modeling. However, their strictly sequential decoding paradigm imposes fundamental constraints on both inference efficiency and modeling flexibility. To address…