Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models

• URL: http://arxiv.org/abs/2604.26365v1
• Date: Wed, 29 Apr 2026 07:22:16 GMT
• Title: Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
• Abstract summary: We propose L2P (Learnable Linear Predictor), a data-driven caching framework that replaces fixed coefficients with learnable per-timestep weights.<n>Rapidly trained in 20 seconds on a single GPU, L2P accurately reconstructs current features from past trajectories.
• Score: 18.678454642609996
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To address the high sampling cost of Diffusion Transformers (DiTs), feature caching offers a training-free acceleration method. However, existing methods rely on hand-crafted forecasting formulas that fail under aggressive skipping. We propose L2P (Learnable Linear Predictor), a simple data-driven caching framework that replaces fixed coefficients with learnable per-timestep weights. Rapidly trained in ~20 seconds on a single GPU, L2P accurately reconstructs current features from past trajectories. L2P significantly outperforms existing baselines: it achieves a 4.55x FLOPs reduction and 4.15x latency speedup on FLUX.1-dev, and maintains high visual fidelity under up to 7.18x acceleration on Qwen-Image models, where prior methods show noticeable quality degradation. Our results show learning linear predictors is highly effective for efficient DiT inference. Code is available at https://github.com/Aredstone/L2P-Cache.

Related papers

• Rethinking Pixel Mean Flows via Interval Denoiser [95.11499828543344]
  We propose the Interval Denoiser, a framework for latent-free generation.<n>Our model achieves an FID of 4.55 in one step (1-NFE) and 3.98 in two steps (2-NFE) without perceptual losses.
  arXiv  Detail & Related papers  (2026-08-05T13:22:43Z)
• Accelerating Rectified Flow Models via Trajectory-Aware Caching [35.13071059415995]
  We propose TACache, a training-free acceleration framework following a skip-then-compensate paradigm.<n>Trajectory-Aware Cache achieves up to 4.14 speedup on text-to-image generation and 2.11 speedup on text-to-video generation.
  arXiv  Detail & Related papers  (2026-05-16T03:44:58Z)
• EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow [52.73538517981873]
  EFlow is an efficient few-step training framework for video diffusion transformers.<n> Gated Local-Global Attention is a token-droppable hybrid block.<n>Path-Drop Guided training replaces the expensive target with a computationally cheap, weak path.
  arXiv  Detail & Related papers  (2026-03-28T02:06:55Z)
• 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)
• Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache [8.614492355393578]
  We propose DPCache, a training-free acceleration framework that formulates diffusion acceleration as a global path planning problem.<n> DPCache employs dynamic programming to select an optimal sequence of key timesteps that minimizes the total path cost while preserving trajectory fidelity.<n>Experiments on DiT, FLUX, and HunyuanVideo demonstrate that DPCache achieves strong acceleration with minimal quality loss.
  arXiv  Detail & Related papers  (2026-02-26T06:13:33Z)
• MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference [11.934900617930774]
  MeanCache is a training-free caching framework for efficient Flow Matching inference.<n>We demonstrate that MeanCache achieves 4.12X and 4.56X and 3.59X acceleration, respectively, while consistently outperforming state-of-the-art caching baselines in generation quality.
  arXiv  Detail & Related papers  (2026-01-27T08:35:50Z)
• ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion [30.897215456167753]
  Diffusion models suffer from substantial computational overhead due to their inherently iterative inference process.<n>We propose ERTACache, a principled caching framework that jointly rectifies both error types.<n>ERTACache achieves up to 2x inference speedup while consistently preserving or even improving visual quality.
  arXiv  Detail & Related papers  (2025-08-27T10:37:24Z)
• CacheQuant: Comprehensively Accelerated Diffusion Models [3.78219736760145]
  CacheQuant is a novel training-free paradigm that comprehensively accelerates diffusion models by jointly optimizing model caching and quantization techniques.<n> Experimental results show that CacheQuant achieves a 5.18 speedup and 4 compression for Stable Diffusion on MS-COCO, with only a 0.02 loss in CLIP score.
  arXiv  Detail & Related papers  (2025-03-03T09:04:51Z)
• Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching [56.286064975443026]
  We make an interesting and somehow surprising observation: the computation of a large proportion of layers in the diffusion transformer, through a caching mechanism, can be readily removed even without updating the model parameters. We introduce a novel scheme, named Learningto-Cache (L2C), that learns to conduct caching in a dynamic manner for diffusion transformers. Experimental results show that L2C largely outperforms samplers such as DDIM and DPM-r, alongside prior cache-based methods at the same inference speed.
  arXiv  Detail & Related papers  (2024-06-03T18:49:57Z)
• DeepCache: Accelerating Diffusion Models for Free [65.02607075556742]
  DeepCache is a training-free paradigm that accelerates diffusion models from the perspective of model architecture. DeepCache capitalizes on the inherent temporal redundancy observed in the sequential denoising steps of diffusion models. Under the same throughput, DeepCache effectively achieves comparable or even marginally improved results with DDIM or PLMS.
  arXiv  Detail & Related papers  (2023-12-01T17:01:06Z)
• StreamYOLO: Real-time Object Detection for Streaming Perception [84.2559631820007]
  We endow the models with the capacity of predicting the future, significantly improving the results for streaming perception. We consider multiple velocities driving scene and propose Velocity-awared streaming AP (VsAP) to jointly evaluate the accuracy. Our simple method achieves the state-of-the-art performance on Argoverse-HD dataset and improves the sAP and VsAP by 4.7% and 8.2% respectively.
  arXiv  Detail & Related papers  (2022-07-21T12:03:02Z)
• Exploiting Activation based Gradient Output Sparsity to Accelerate Backpropagation in CNNs [15.465530153038927]
  Machine/deep-learning (ML/DL) based techniques are emerging as a driving force behind many cutting-edge technologies. However, training these models involving large parameters is both time-consuming and energy-hogging.
  arXiv  Detail & Related papers  (2021-09-16T04:12:51Z)

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.