DriveCache: Action-Aware Caching for Driving World Model Inference
- URL: http://arxiv.org/abs/2608.16354v1
- Date: Mon, 17 Aug 2026 10:04:49 GMT
- Title: DriveCache: Action-Aware Caching for Driving World Model Inference
- Abstract summary: Diffusion-based driving generators evaluate large backbones across denoising steps, which limits generation throughput.<n>Existing diffusion acceleration methods reduce this cost, but general-purpose designs omit driving signals available before generation, such as ego speed and planned trajectories.<n>We propose DriveCache, a training-free, action-aware controller that uses planned motion to allocate reuse across scenes and dynamic programming to place it across denoising steps under a calibrated response budget.
- Score: 61.07117287683939
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Driving video generation models support autonomous-driving development by predicting controllable future scenes for simulation, planning evaluation, and offline data generation. Diffusion-based driving generators repeatedly evaluate large backbones across denoising steps, which limits generation throughput. Existing diffusion acceleration methods reduce this cost, but general-purpose designs omit driving signals available before generation, such as ego speed and planned trajectories. Experiments across driving motions show that cache tolerance varies with ego translation and rotation, denoising progress, and consecutive reuse length. We propose DriveCache, a training-free, action-aware controller that uses planned motion to allocate reuse across scenes and dynamic programming to place it across denoising steps under a calibrated response budget. A causal drift check refreshes features and replans the remaining schedule when generation departs from calibration. Across three generator configurations, DriveCache improves the overall fidelity-efficiency trade-off over evaluated cache methods. Our code will be publicly available.
Related papers
- NaviCache: Test-Time Self-Calibration Caching for Video Generation [82.90113757454375]
NaviCache is a test-time self-calibration method for Video Diffusion Models.<n>It bridges the fundamental domain gap and the non-stationary nature of diffusion.<n>It provides a theoretically grounded mechanism for error-bounded skipping.
arXiv Detail & Related papers (2026-06-25T09:28:12Z) - Muninn: Your Trajectory Diffusion Model But Faster [4.221836692945716]
Diffusion-based trajectory planners can synthesize rich, multimodal robot motions, but their iterative denoising makes online planning and control prohibitively slow.<n>We address the problem of making diffusion-based trajectory planners fast enough for real-time robot use without retraining the model or sacrificing trajectory quality.<n>Muninn delivers up to 4.6x wall-clock speedups across several trajectory diffusion models by reducing denoiser evaluations, while preserving task performance and safety metrics.
arXiv Detail & Related papers (2026-05-11T05:21:52Z) - X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference [37.22440439525785]
We present X-Cache, a training-free acceleration method that caches across consecutive generation chunks rather than across denoising steps.<n>X-Cache achieves 71% block skip rate with 2.6x wall-clock speedup while maintaining minimum degradation.
arXiv Detail & Related papers (2026-04-22T07:36:59Z) - WorldCache: Content-Aware Caching for Accelerated Video World Models [50.7543797435026]
We present textbfWorldCache, a Perception-Constrained Dynamic CaCache framework.<n>WorldCache improves both when and how to reuse features.<n>On Cosmos-2.5-2B evaluated on PAI-Bench, WorldCache achieves textbf$2.3times$ inference speedup while preserving textbf99.4% of baseline quality.
arXiv Detail & Related papers (2026-03-23T17:59:54Z) - SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching [75.02865981328509]
Caching reduces computation by reusing previously computed model outputs across timesteps.<n>We propose Sensitivity-Aware Caching (SenCache), a dynamic caching policy that adaptively selects caching timesteps on a per-sample basis.<n>SenCache achieves better visual quality than existing caching methods under similar computational budgets.
arXiv Detail & Related papers (2026-02-27T17:36:09Z) - Adaptive Time Step Flow Matching for Autonomous Driving Motion Planning [8.384289409828678]
A prevailing approach is large-scale imitation learning on expert driving datasets, aimed at generalizing across diverse real-world scenarios.<n>For online trajectory generation, such methods must operate at real-time rates.<n>We propose a framework based on conditional flow matching that jointly predicts future motions of surrounding agents and plans the ego trajectory in real time.
arXiv Detail & Related papers (2026-02-10T20:57:01Z) - Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generation [50.04968365065964]
Diffusion-based talking head models generate high-quality, photorealistic videos but suffer from slow inference.<n>We introduce Lightning-fast Caching-based Parallel denoising prediction (LightningCP)<n>We also propose Decoupled Foreground Attention (DFA) to further accelerate attention computations.
arXiv Detail & Related papers (2025-08-25T02:58:39Z) - Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model [63.336123527432136]
We introduce Bench2Drive-R, a generative framework that enables reactive closed-loop evaluation.<n>Unlike existing video generative models for autonomous driving, the proposed designs are tailored for interactive simulation.<n>We compare the generation quality of Bench2Drive-R with existing generative models and achieve state-of-the-art performance.
arXiv Detail & Related papers (2024-12-11T06:35:18Z)
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.