WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation

• URL: http://arxiv.org/abs/2607.23265v2
• Date: Mon, 03 Aug 2026 14:35:14 GMT
• Title: WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation
• Abstract summary: WaveZip is a joint signal-frequency-domain framework for efficient video inference.<n> experiments on long video understanding benchmarks demonstrate that WaveZip retains 99.6% of the full performance.
• Score: 69.37452950816122
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing Large Vision-Language Models (LVLMs) struggle with long-form video understanding due to the quadratic computational cost of visual tokens. While recent efficient methods attempt to compress tokens via hard pruning or uniform merging, they operate strictly in the spatial feature domain, where robust structural context and discriminative semantic details are inherently entangled. In this work, we propose WaveZip, a joint signal-frequency-domain framework for efficient video inference. Driven by the insight that temporal redundancy resides in low-pass approximation scales while spatial saliency strongly correlates with high-frequency components, WaveZip leverages Discrete Wavelet Transforms (DWT) to disentangle these signals. Temporally, it employs 1D DWT to analyze query-frame relevance, and the resulting high-frequency coefficients are further gated by inter-frame differences, with both signals jointly driving the dynamic allocation of a precise frame-level token budget. Spatially, a 2D DWT decomposes features into low-frequency approximations and high-frequency detail components, where the high-frequency coefficients are modulated within query-salient regions to regulate spatial reconstruction. Importantly, WaveZip requires no task-specific training and can be seamlessly integrated into off-the-shelf LVLMs to boost inference efficiency. Extensive experiments on long video understanding benchmarks demonstrate that WaveZip retains 99.6% of the full performance under an extreme 10x compression ratio, consistently outperforming state-of-the-art methods.

Related papers

• FATE: Pillar Encoding and Frequency-Aware Training for Event-Based Object Detection [0.0]
  Event cameras offer inherent advantages in high-speed and high-dynamic-range scenarios.<n>Current approaches partition the accumulation window into fixed temporal sub-bins.<n>We propose FATE, a unified framework built upon a novel spatial framework.
  arXiv  Detail & Related papers  (2026-06-15T22:32:09Z)
• 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)
• ANTIC: Adaptive Neural Temporal In-situ Compressor [19.44325026786871]
  Large-scale and high-dimensional partial differential equations (PDEs) have reached the petabyte-to-exabyte scale.<n>ANTIC enables a combined compression temporal and spatial components and effectively alleviates the need for explicit on-disk storage of entire time-resolution.<n> Experimental results demonstrate how storage reductions of several orders of magnitude relate to physics accuracy.
  arXiv  Detail & Related papers  (2026-04-10T17:58:16Z)
• SONAR: Spectral-Contrastive Audio Residuals for Generalizable Deepfake Detection [6.042897432654865]
  Spectral-cONtrastive Audio Residuals (AR) is a frequency-guided framework for deepfake audio detectors.<n>AR disentangles an audio signal into complementary representations.<n> evaluated on the ASVspoof 2021 and in-the-wild benchmarks.
  arXiv  Detail & Related papers  (2025-11-26T12:16:38Z)
• FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Clouds [52.997038111673966]
  FLaTEC is a frequency-aware compression model that enables the compression of a full scan with high compression ratios.<n>We convert voxelized embeddings into triplane representations to reduce sparsity, computational cost, and storage requirements.<n>Our method achieves state-of-the-art rate-distortion performance and outperforms the standard codecs by 78% and 94% in BD-rate on both datasets.
  arXiv  Detail & Related papers  (2025-11-25T08:37:49Z)
• Bidirectional Feature-aligned Motion Transformation for Efficient Dynamic Point Cloud Compression [97.66080040613726]
  We propose a Bidirectional Feature-aligned Motion Transformation (Bi-FMT) framework that implicitly models motion in the feature space.<n>Bi-FMT aligns features across both past and future frames to produce temporally consistent latent representations.<n>We show Bi-FMT surpasses D-DPCC and AdaDPCC in both compression efficiency and runtime.
  arXiv  Detail & Related papers  (2025-09-18T03:51:06Z)
• FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion [92.4205087439928]
  Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability.<n>We propose the Self-supervised Transfer (PST) and the FrequencyDe-coupled Fusion module (FreDF)<n>PST establishes cross-modal knowledge transfer through latent space alignment with image foundation models, effectively mitigating data scarcity.<n>FreDF explicitly decouples high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches.<n>This combined approach enables FUSE to construct a universal image-event that only requires lightweight decoder adaptation for target datasets.
  arXiv  Detail & Related papers  (2025-03-25T15:04:53Z)
• Dynamic Frame Interpolation in Wavelet Domain [57.25341639095404]
  Video frame is an important low-level computation vision task, which can increase frame rate for more fluent visual experience. Existing methods have achieved great success by employing advanced motion models and synthesis networks. WaveletVFI can reduce computation up to 40% while maintaining similar accuracy, making it perform more efficiently against other state-of-the-arts.
  arXiv  Detail & Related papers  (2023-09-07T06:41:15Z)

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.