HiCache: Training-free Acceleration of Diffusion Models via Hermite Polynomial-based Feature Caching

Diffusion models have achieved remarkable success in content generation but suffer from prohibitive computational costs due to iterative sampling. While recent feature caching methods tend to accelerate inference through temporal extrapolation, these methods still suffer from server quality loss due to the failure in modeling the complex dynamics of feature evolution. To solve this problem, this paper presents HiCache, a training-free acceleration framework that fundamentally improves feature prediction by aligning mathematical tools with empirical properties. Our key insight is that feature derivative approximations in Diffusion Transformers exhibit multivariate Gaussian characteristics, motivating the use of Hermite polynomials-the potentially theoretically optimal basis for Gaussian-correlated processes. Besides, We further introduce a dual-scaling mechanism that ensures numerical stability while preserving predictive accuracy. Extensive experiments demonstrate HiCache's superiority: achieving 6.24x speedup on FLUX.1-dev while exceeding baseline quality, maintaining strong performance across text-to-image, video generation, and super-resolution tasks. Core implementation is provided in the appendix, with complete code to be released upon acceptance.

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models

Vision-Language-Action (VLA) models, particularly diffusion-based architectures, demonstrate transformative potential for embodied intelligence but are severely hampered by high computational and memory demands stemming from extensive inherent and inference-time redundancies. While existing acceleration efforts often target isolated inefficiencies, such piecemeal solutions typically fail to holistically address the varied computational and memory bottlenecks across the entire VLA pipeline, thereby limiting practical deployability. We introduce EfficientVLA, a structured and training-free inference acceleration framework that systematically eliminates these barriers by cohesively exploiting multifaceted redundancies. EfficientVLA synergistically integrates three targeted strategies: (1) pruning of functionally inconsequential layers from the language module, guided by an analysis of inter-layer redundancies; (2) optimizing the visual processing pathway through a task-aware strategy that selects a compact, diverse set of visual tokens, balancing task-criticality with informational coverage; and (3) alleviating temporal computational redundancy within the iterative diffusion-based action head by strategically caching and reusing key intermediate features. We apply our method to a standard VLA model CogACT, yielding a 1.93X inference speedup and reduces FLOPs to 28.9%, with only a 0.6% success rate drop in the SIMPLER benchmark.

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

The rapid advancement of large language models (LLMs) and multi-modal LLMs (MLLMs) has historically relied on model-centric scaling through increasing parameter counts from millions to hundreds of billions to drive performance gains. However, as we approach hardware limits on model size, the dominant computational bottleneck has fundamentally shifted to the quadratic cost of self-attention over long token sequences, now driven by ultra-long text contexts, high-resolution images, and extended videos. In this position paper, \textbf{we argue that the focus of research for efficient AI is shifting from model-centric compression to data-centric compression}. We position token compression as the new frontier, which improves AI efficiency via reducing the number of tokens during model training or inference. Through comprehensive analysis, we first examine recent developments in long-context AI across various domains and establish a unified mathematical framework for existing model efficiency strategies, demonstrating why token compression represents a crucial paradigm shift in addressing long-context overhead. Subsequently, we systematically review the research landscape of token compression, analyzing its fundamental benefits and identifying its compelling advantages across diverse scenarios. Furthermore, we provide an in-depth analysis of current challenges in token compression research and outline promising future directions. Ultimately, our work aims to offer a fresh perspective on AI efficiency, synthesize existing research, and catalyze innovative developments to address the challenges that increasing context lengths pose to the AI community's advancement.

EEdit : Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing

Inversion-based image editing is rapidly gaining momentum while suffering from significant computation overhead, hindering its application in real-time interactive scenarios. In this paper, we rethink that the redundancy in inversion-based image editing exists in both the spatial and temporal dimensions, such as the unnecessary computation in unedited regions and the redundancy in the inversion progress. To tackle these challenges, we propose a practical framework, named EEdit, to achieve efficient image editing. Specifically, we introduce three techniques to solve them one by one. For spatial redundancy, spatial locality caching is introduced to compute the edited region and its neighboring regions while skipping the unedited regions, and token indexing preprocessing is designed to further accelerate the caching. For temporal redundancy, inversion step skipping is proposed to reuse the latent for efficient editing. Our experiments demonstrate an average of 2.46 $\times$ acceleration without performance drop in a wide range of editing tasks including prompt-guided image editing, dragging and image composition. Our codes are available at https://github.com/yuriYanZeXuan/EEdit

From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers

Diffusion Transformers (DiT) have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. To solve this problem, feature caching has been proposed to accelerate diffusion models by caching the features in the previous timesteps and then reusing them in the following timesteps. However, at timesteps with significant intervals, the feature similarity in diffusion models decreases substantially, leading to a pronounced increase in errors introduced by feature caching, significantly harming the generation quality. To solve this problem, we propose TaylorSeer, which firstly shows that features of diffusion models at future timesteps can be predicted based on their values at previous timesteps. Based on the fact that features change slowly and continuously across timesteps, TaylorSeer employs a differential method to approximate the higher-order derivatives of features and predict features in future timesteps with Taylor series expansion. Extensive experiments demonstrate its significant effectiveness in both image and video synthesis, especially in high acceleration ratios. For instance, it achieves an almost lossless acceleration of 4.99$\times$ on FLUX and 5.00$\times$ on HunyuanVideo without additional training. On DiT, it achieves $3.41$ lower FID compared with previous SOTA at $4.53$$\times$ acceleration. %Our code is provided in the supplementary materials and will be made publicly available on GitHub. Our codes have been released in Github:https://github.com/Shenyi-Z/TaylorSeer

Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free

Stable Diffusion has achieved remarkable success in the field of text-to-image generation, with its powerful generative capabilities and diverse generation results making a lasting impact. However, its iterative denoising introduces high computational costs and slows generation speed, limiting broader adoption. The community has made numerous efforts to reduce this computational burden, with methods like feature caching attracting attention due to their effectiveness and simplicity. Nonetheless, simply reusing features computed at previous timesteps causes the features across adjacent timesteps to become similar, reducing the dynamics of features over time and ultimately compromising the quality of generated images. In this paper, we introduce a dynamics-aware token pruning (DaTo) approach that addresses the limitations of feature caching. DaTo selectively prunes tokens with lower dynamics, allowing only high-dynamic tokens to participate in self-attention layers, thereby extending feature dynamics across timesteps. DaTo combines feature caching with token pruning in a training-free manner, achieving both temporal and token-wise information reuse. Applied to Stable Diffusion on the ImageNet, our approach delivered a 9$\times$ speedup while reducing FID by 0.33, indicating enhanced image quality. On the COCO-30k, we observed a 7$\times$ acceleration coupled with a notable FID reduction of 2.17.

Accelerating Diffusion Transformers with Dual Feature Caching

Diffusion Transformers (DiT) have become the dominant methods in image and video generation yet still suffer substantial computational costs. As an effective approach for DiT acceleration, feature caching methods are designed to cache the features of DiT in previous timesteps and reuse them in the next timesteps, allowing us to skip the computation in the next timesteps. However, on the one hand, aggressively reusing all the features cached in previous timesteps leads to a severe drop in generation quality. On the other hand, conservatively caching only the features in the redundant layers or tokens but still computing the important ones successfully preserves the generation quality but results in reductions in acceleration ratios. Observing such a tradeoff between generation quality and acceleration performance, this paper begins by quantitatively studying the accumulated error from cached features. Surprisingly, we find that aggressive caching does not introduce significantly more caching errors in the caching step, and the conservative feature caching can fix the error introduced by aggressive caching. Thereby, we propose a dual caching strategy that adopts aggressive and conservative caching iteratively, leading to significant acceleration and high generation quality at the same time. Besides, we further introduce a V-caching strategy for token-wise conservative caching, which is compatible with flash attention and requires no training and calibration data. Our codes have been released in Github: \textbf{Code: \href{https://github.com/Shenyi-Z/DuCa}{\texttt{\textcolor{cyan}{https://github.com/Shenyi-Z/DuCa}}}}

Accelerating Diffusion Transformers with Token-wise Feature Caching

Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion transformers by caching the features in previous timesteps and reusing them in the following timesteps. However, previous caching methods ignore that different tokens exhibit different sensitivities to feature caching, and feature caching on some tokens may lead to 10$\times$ more destruction to the overall generation quality compared with other tokens. In this paper, we introduce token-wise feature caching, allowing us to adaptively select the most suitable tokens for caching, and further enable us to apply different caching ratios to neural layers in different types and depths. Extensive experiments on PixArt-$\alpha$, OpenSora, and DiT demonstrate our effectiveness in both image and video generation with no requirements for training. For instance, 2.36$\times$ and 1.93$\times$ acceleration are achieved on OpenSora and PixArt-$\alpha$ with almost no drop in generation quality.