SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing

• URL: http://arxiv.org/abs/2603.08982v1
• Date: Mon, 09 Mar 2026 22:15:31 GMT
• Title: SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing
• Abstract summary: Diffusion Transformers (DiTs) have become a leading backbone for video generation, yet their quadratic attention cost remains a major bottleneck.<n>In this paper, we show that the missing contributions can be recovered without training.<n>We introduce SVG-EAR, a parameter-free linear compensation branch that uses the centroid to approximate skipped blocks and recover their contributions.
• Score: 77.91660464664615
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion Transformers (DiTs) have become a leading backbone for video generation, yet their quadratic attention cost remains a major bottleneck. Sparse attention reduces this cost by computing only a subset of attention blocks. However, prior methods often either drop the remaining blocks, which incurs information loss, or rely on learned predictors to approximate them, introducing training overhead and potential output distribution shifting. In this paper, we show that the missing contributions can be recovered without training: after semantic clustering, keys and values within each block exhibit strong similarity and can be well summarized by a small set of cluster centroids. Based on this observation, we introduce SVG-EAR, a parameter-free linear compensation branch that uses the centroid to approximate skipped blocks and recover their contributions. While centroid compensation is accurate for most blocks, it can fail on a small subset. Standard sparsification typically selects blocks by attention scores, which indicate where the model places its attention mass, but not where the approximation error would be largest. SVG-EAR therefore performs error-aware routing: a lightweight probe estimates the compensation error for each block, and we compute exactly the blocks with the highest error-to-cost ratio while compensating for skipped blocks. We provide theoretical guarantees that relate attention reconstruction error to clustering quality, and empirically show that SVG-EAR improves the quality-efficiency trade-off and increases throughput at the same generation fidelity on video diffusion tasks. Overall, SVG-EAR establishes a clear Pareto frontier over prior approaches, achieving up to 1.77$\times$ and 1.93$\times$ speedups while maintaining PSNRs of up to 29.759 and 31.043 on Wan2.2 and HunyuanVideo, respectively.

Related papers

• Packet-Loss Robust 3D Gaussian Compression via Atomic Packaging and GNN-based Error Concealment [3.679539308969595]
  We propose a packet-loss robust 3DGS transmission and error concealment framework.<n>A lightweight two-layer graph neural network with cross-attention over hash-grid priors refines high-frequency attribute residuals.<n> Experiments under 20 percent random packet loss on BungeeNeRF, Mip-NeRF 360, and Tanks and Temples show that the proposed method substantially improves over no-concealment transmission.
  arXiv  Detail & Related papers  (2026-07-20T13:13:38Z)
• Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysis [14.63838637349137]
  In 3D point cloud understanding, the core challenge lies in accurately capturing discriminative features within complex neighborhoods.<n>Existing methods explore feature correlation discrimination but are limited to point-level spatial distribution or channel responses.<n>We propose PointCRA, a novel network with a channel-level metric-based enhancement mechanism.
  arXiv  Detail & Related papers  (2026-05-04T08:59:36Z)
• The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment [24.22523653033535]
  Vision-Language Models learn a shared embedding space for images and text, yet their representations remain geometrically separated.<n>This gap limits tasks requiring cross-modal interchangeability, such as captioning and joint clustering.<n>We propose TPC-CMA (Three-Phase Curriculum for Cross-Modal Alignment), a fine-tuning framework that explicitly reduces both components.
  arXiv  Detail & Related papers  (2026-03-31T22:11:49Z)
• Robust inverse material design with physical guarantees using the Voigt-Reuss Net [0.0]
  We propose a spectrally normalized surrogate for forward and inverse mechanical homogenization with hard physical guarantees.<n>In 3D linear elasticity on an open dataset of biphasic microstructures, a fully connected Voigt-Reuss net trained on $>!7.5times 105$ FFT-based labels with 236 isotropy-in descriptors.<n>Overall, the Voigt-Reuss net unifies accurate, physically admissible forward prediction with large-batch, constraint-consistent inverse design.
  arXiv  Detail & Related papers  (2025-11-14T15:17:37Z)
• Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation [84.00166854547241]
  Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention.<n>We propose SVG2, a training-free framework that maximizes identification accuracy and computation minimizes waste.
  arXiv  Detail & Related papers  (2025-05-24T21:30:29Z)
• Sparse Linear Bandits with Blocking Constraints [22.01704171400845]
  We investigate the high-dimensional sparse linear bandits problem in a data-poor regime.<n>We show novel offline statistical guarantees of the lasso estimator for the linear model.<n>We propose a meta-algorithm based on corralling that does not need knowledge of optimal sparsity parameter $k$ at minimal cost to regret.
  arXiv  Detail & Related papers  (2024-10-26T01:42:03Z)
• Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction [82.72686460985297]
  We tackle the problem of estimating a Manhattan frame. We derive two new 2-line solvers, one of which does not suffer from singularities affecting existing solvers. We also design a new non-minimal method, running on an arbitrary number of lines, to boost the performance in local optimization.
  arXiv  Detail & Related papers  (2023-08-21T13:03:25Z)
• 1$\ imes$N Block Pattern for Network Sparsity [90.43191747596491]
  We propose one novel concept of $1times N$ block sparsity pattern (block pruning) to break this limitation. Our pattern obtains about 3.0% improvements over filter pruning in the top-1 accuracy of MobileNet-V2. It also obtains 56.04ms inference savings on Cortex-A7 CPU over weight pruning.
  arXiv  Detail & Related papers  (2021-05-31T05:50:33Z)
• Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation [51.17232267143098]
  We propose a novel system named Disp R-CNN for 3D object detection from stereo images. We use a statistical shape model to generate dense disparity pseudo-ground-truth without the need of LiDAR point clouds. Experiments on the KITTI dataset show that, even when LiDAR ground-truth is not available at training time, Disp R-CNN achieves competitive performance and outperforms previous state-of-the-art methods by 20% in terms of average precision.
  arXiv  Detail & Related papers  (2020-04-07T17:48:45Z)
• Discrimination-aware Network Pruning for Deep Model Compression [79.44318503847136]
  Existing pruning methods either train from scratch with sparsity constraints or minimize the reconstruction error between the feature maps of the pre-trained models and the compressed ones. We propose a simple-yet-effective method called discrimination-aware channel pruning (DCP) to choose the channels that actually contribute to the discriminative power. Experiments on both image classification and face recognition demonstrate the effectiveness of our methods.
  arXiv  Detail & Related papers  (2020-01-04T07:07:41Z)

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.