Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers

• URL: http://arxiv.org/abs/2602.18093v1
• Date: Fri, 20 Feb 2026 09:33:59 GMT
• Title: Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers
• Authors: Hanshuai Cui, Zhiqing Tang, Qianli Ma, Zhi Yao, Weijia Jia,
• Abstract summary: Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation.<n>We propose textbfPrediT, a training-free acceleration framework that formulates feature prediction as a linear multistep problem.<n>Our method achieves up to $5.54times$ latency reduction across various DiT-based image and video generation models, while incurring negligible quality degradation.
• Score: 10.751183015853863
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 feature caching and reuse under the assumption of temporal stability. However, reusing features for multiple steps may lead to latent drift and visual degradation. We observe that model outputs evolve smoothly along much of the diffusion trajectory, enabling principled predictions rather than naive reuse. Based on this insight, we propose \textbf{PrediT}, a training-free acceleration framework that formulates feature prediction as a linear multistep problem. We employ classical linear multistep methods to forecast future model outputs from historical information, combined with a corrector that activates in high-dynamics regions to prevent error accumulation. A dynamic step modulation mechanism adaptively adjusts the prediction horizon by monitoring the feature change rate. Together, these components enable substantial acceleration while preserving generation fidelity. Extensive experiments validate that our method achieves up to $5.54\times$ latency reduction across various DiT-based image and video generation models, while incurring negligible quality degradation.

Related papers

• Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration [58.19554276924402]
  We propose spectral diffusion feature forecaster (Spectrum) to enable global, long-range feature reuse with tightly controlled error.<n>We achieve up to 4.79$times$ speedup on FLUX.1 and 4.67$times$ speedup on Wan2.1-14B, while maintaining much higher sample quality compared with the baselines.
  arXiv  Detail & Related papers  (2026-03-02T08:59:11Z)
• Look-Ahead and Look-Back Flows: Training-Free Image Generation with Trajectory Smoothing [3.77130368225397]
  Various training-free flow matching approaches have been developed to improve image generation through flow velocity field adjustment.<n>We propose two training-free trajectory smoothing schemes: emphLook-Ahead, which averages the current and next-step latents using a curvature-gated weight, and emphLook-Back, which smoothes latents using an exponential moving average with decay.
  arXiv  Detail & Related papers  (2026-02-10T06:34:47Z)
• Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers [19.107716099809707]
  Diffusion Transformers (DiTs) have demonstrated exceptional performance in high-fidelity image and video generation.<n>Current methods often struggle to maintain generation quality at high acceleration ratios.<n>We propose FoCa, which treats feature caching as a feature-ODE solving problem.
  arXiv  Detail & Related papers  (2025-08-22T08:34:03Z)
• Sortblock: Similarity-Aware Feature Reuse for Diffusion Model [9.749736545966694]
  Diffusion Transformers (DiTs) have demonstrated remarkable generative capabilities.<n>DiTs' sequential denoising process results in high inference latency.<n>We propose Sortblock, a training-free inference acceleration framework.
  arXiv  Detail & Related papers  (2025-08-01T08:10:54Z)
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion [67.94300151774085]
  We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models.<n>It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their own imperfect outputs.
  arXiv  Detail & Related papers  (2025-06-09T17:59:55Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Generative Pre-trained Autoregressive Diffusion Transformer [74.25668109048418]
  GPDiT is a Generative Pre-trained Autoregressive Diffusion Transformer.<n>It unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis.<n>It autoregressively predicts future latent frames using a diffusion loss, enabling natural modeling of motion dynamics.
  arXiv  Detail & Related papers  (2025-05-12T08:32:39Z)
• Accelerating Diffusion Transformer via Increment-Calibrated Caching with Channel-Aware Singular Value Decomposition [4.0594792247165]
  Diffusion transformer (DiT) models have achieved remarkable success in image generation.<n>We propose increment-calibrated caching, a training-free method for DiT acceleration.<n>Our method eliminates more than 45% and improves IS by 12 at the cost of less than 0.06 FID increase.
  arXiv  Detail & Related papers  (2025-05-09T06:56:17Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints [51.83081671798784]
  Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability.<n>DiT's practical application suffers from inherent dynamic feature instability, leading to error amplification during cached inference.<n>We propose Skip-DiT, an image and video generative DiT variant enhanced with Long-Skip-Connections (LSCs) - the key efficiency component in U-Nets.
  arXiv  Detail & Related papers  (2024-11-26T17:28:10Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.