Related papers: ERTACache: Error Rectification and Timesteps Adjus…

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…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Real-world applications of neural language models often involve running many different models over the same corpus. The high computational cost of these runs has led to interest in techniques that can reuse the contextualized embeddings…

Diffusion models are a powerful class of generative models that iteratively denoise samples to produce data. While many works have focused on the number of iterations in this sampling procedure, few have focused on the cost of each…

Diffusion models have emerged as powerful generative models, but their high computation cost in iterative sampling remains a significant bottleneck. In this work, we present an in-depth and insightful study of state-of-the-art acceleration…

Diffusion models produce realistic images and videos but require substantial computational resources, necessitating multi-accelerator parallelism for real-time deployment. However, parallel inference introduces significant communication…

In this paper, we address the performance degradation of efficient diffusion models by introducing Multi-architecturE Multi-Expert diffusion models (MEME). We identify the need for tailored operations at different time-steps in diffusion…

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy…

Diffusion models achieve great success in generating diverse and high-fidelity images, yet their widespread application, especially in real-time scenarios, is hampered by their inherently slow generation speed. The slow generation stems…

Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation, yet their iterative denoising process incurs high computational costs. Existing training-free acceleration methods rely on…

The rapid progress in artificial intelligence-generated content (AIGC), especially with diffusion models, has significantly advanced development of high-quality video generation. However, current video diffusion models exhibit demanding…

The substantial computational costs of diffusion models, especially due to the repeated denoising steps necessary for high-quality image generation, present a major obstacle to their widespread adoption. While several studies have attempted…

Diffusion probabilistic models (DPMs) have achieved impressive success in visual generation. While, they suffer from slow inference speed due to iterative sampling. Employing fewer sampling steps is an intuitive solution, but this will also…

Autoregressive models, often built on Transformer architectures, represent a powerful paradigm for generating ultra-long videos by synthesizing content in sequential chunks. However, this sequential generation process is notoriously slow.…

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…

Vision-language models (VLMs) exhibit remarkable zero-shot capabilities but struggle with distribution shifts in downstream tasks when labeled data is unavailable, which has motivated the development of Test-Time Adaptation (TTA) to improve…

Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which…

Caching is crucial for system performance, but the delayed hit phenomenon, where requests queue during lengthy fetches after a cache miss, significantly degrades user-perceived latency in modern high-throughput systems. While prior works…

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the quadratic complexity of full attention. Training-free sparse attention is attractive…