Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation

• URL: http://arxiv.org/abs/2604.12219v1
• Date: Tue, 14 Apr 2026 02:51:52 GMT
• Title: Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation
• Abstract summary: Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention.<n>We propose Precision-Allocated Sparse Attention (PASA), a training-free framework designed for highly efficient and temporally smooth video generation.
• Score: 9.132288507881592
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. While sparse attention provides a promising acceleration solution, existing methods frequently provoke severe visual flickering caused by static sparsity patterns and deterministic block routing. To resolve these limitations, we propose Precision-Allocated Sparse Attention (PASA), a training-free framework designed for highly efficient and temporally smooth video generation. First, we implement a curvature-aware dynamic budgeting mechanism. By profiling the generation trajectory acceleration across timesteps, we elastically allocate the exact-computation budget to secure high-precision processing strictly during critical semantic transitions. Second, we replace global homogenizing estimations with hardware-aligned grouped approximations, successfully capturing fine-grained local variations while maintaining peak compute throughput. Finally, we incorporate a stochastic selection bias into the attention routing mechanism. This probabilistic approach softens rigid selection boundaries and eliminates selection oscillation, effectively eradicating the localized computational starvation that drives temporal flickering. Extensive evaluations on leading video diffusion models demonstrate that PASA achieves substantial inference acceleration while consistently producing remarkably fluid and structurally stable video sequences.

Related papers

• Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model [88.42070387375679]
  We introduce Flex-Forcing, a unified training and inference framework that enables a video diffusion model to seamlessly operate under both bidirectional and autoregressive generation regimes.<n>Experiments on multiple video generation benchmarks demonstrate that Flex-Forcing achieves consistently better video quality, long-video stability than strong baselines with a rigid inference schedule.
  arXiv  Detail & Related papers  (2026-07-03T17:34:14Z)
• RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling [51.279397568734424]
  Video generation models based on Diffusion Transformers (DiTs) have achieved remarkable performance in video synthesis.<n>DiTs suffer from high inference latency and computational costs due to the quadratic complexity of 3D attention.<n>We introduce bftextRhymeFlow, a training-free framework that decouples the denoising trajectories of different frames.
  arXiv  Detail & Related papers  (2026-06-04T15:49:37Z)
• Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers [12.948398661304184]
  Diffusion-APO is a trajectory-aware algorithm for aligning video diffusion models with human intent.<n>We introduce a unified and modular RLHF framework that integrates online ranking, half-online anchoring, offline refinement, and distillation-aware drift correction.<n>We demonstrate that Diffusion-APO consistently outperforms standard baselines in visual quality and instruction following.
  arXiv  Detail & Related papers  (2026-05-08T09:37:46Z)
• GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting [71.12303582606019]
  Continuous Video Super-Resolution (C-STVSR) aims to simultaneously enhance the spatial and frame rate of videos by arbitrary scale factors.<n>We propose GS-STVSR, an ultra-efficient C-STVSR framework based on 2D Gaussianting (2D-GS)<n>We show that GS-STVSR achieves state-of-the-art quality across all benchmarks.
  arXiv  Detail & Related papers  (2026-04-20T10:11:05Z)
• Motion-Adaptive Temporal Attention for Lightweight Video Generation with Stable Diffusion [1.9349092719498848]
  We present a motion-adaptive temporal attention mechanism for parameter-efficient video generation built upon frozen Stable Diffusion models.<n>We inject lightweight temporal attention modules into all UNet transformer blocks via a cascaded strategy.<n>Our ablation studies reveal a clear trade-off between noise correlation and motion amplitude, providing a practical inference-time control for diverse generation behaviors.
  arXiv  Detail & Related papers  (2026-03-18T06:20:57Z)
• Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models [58.3184497327891]
  Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences.<n>We present Astrolabe, an efficient online reinforcement learning framework tailored for distilled AR models.
  arXiv  Detail & Related papers  (2026-03-17T18:32:18Z)
• Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers [10.751183015853863]
  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.
  arXiv  Detail & Related papers  (2026-02-20T09:33:59Z)
• LiteAttention: A Temporal Sparse Attention for Diffusion Transformers [1.3471268811218626]
  LiteAttention exploits temporal coherence to enable evolutionary computation skips across the denoising sequence.<n>We implement a highly optimized LiteAttention kernel on top of FlashAttention and demonstrate substantial speedups on production video diffusion models.
  arXiv  Detail & Related papers  (2025-11-14T08:26:55Z)
• Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events [71.2439653098351]
  Continuous space-time video super-STVSR has garnered increasing interest for its capability to reconstruct high-resolution and high-frame-rate videos at arbitrary temporal scales.<n>We present EvEnhancer, a novel approach that marries unique properties of high temporal and high dynamic range encapsulated in event streams.<n>Our method achieves state-of-the-art performance on both synthetic and real-world datasets, while maintaining generalizability at OOD scales.
  arXiv  Detail & Related papers  (2025-10-04T15:23:07Z)
• DiTVR: Zero-Shot Diffusion Transformer for Video Restoration [48.97196894658511]
  DiTVR is a zero shot video restoration framework that couples a diffusion transformer with trajectory aware attention and a flow consistent sampler.<n>Our attention mechanism aligns tokens along optical flow trajectories, with particular emphasis on vital layers that exhibit the highest sensitivity to temporal dynamics.<n>The flow guided sampler injects data consistency only into low-frequency bands, preserving high frequency priors while accelerating cache.
  arXiv  Detail & Related papers  (2025-08-11T09:54:45Z)
• VDEGaussian: Video Diffusion Enhanced 4D Gaussian Splatting for Dynamic Urban Scenes Modeling [68.65587507038539]
  We present a novel video diffusion-enhanced 4D Gaussian Splatting framework for dynamic urban scene modeling.<n>Our key insight is to distill robust, temporally consistent priors from a test-time adapted video diffusion model.<n>Our method significantly enhances dynamic modeling, especially for fast-moving objects, achieving an approximate PSNR gain of 2 dB.
  arXiv  Detail & Related papers  (2025-08-04T07:24:05Z)
• 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)

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.