Rethinking Video Token Compression with a Global Codebook: Learning Once, Compressing Everywhere

• URL: http://arxiv.org/abs/2608.01271v1
• Date: Sun, 02 Aug 2026 14:24:13 GMT
• Title: Rethinking Video Token Compression with a Global Codebook: Learning Once, Compressing Everywhere
• Abstract summary: Video large language models (Video-LLMs) represent videos as dense sequences of visual tokens, whose length grows with the temporal and spatial extent of the input.<n>Existing token compression methods, including pruning and merging, perform compression online during inference.<n>We propose textbfONCE, a plug-in video token compression framework that introduces an offline-to-online paradigm.
• Score: 5.7189025167000205
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video large language models (Video-LLMs) represent videos as dense sequences of visual tokens, whose length grows with the temporal and spatial extent of the input. These tokens often contain substantial redundancy arising from repeated visual patterns, leading to unnecessary computation in the subsequent language-model processing. Existing token compression methods, including pruning and merging, perform compression online during inference, repeatedly incurring additional computation for each input video and often relying on model-specific designs that limit their generality, we instead rethink this paradigm by shifting the costly compression process offline. We propose \textbf{ONCE}, a plug-in video token compression framework that introduces an offline-to-online paradigm: a frequency-aware global codebook is learned once in the visual feature space and reused for lightweight online compression through codebook lookup and aggregation, reducing repeated per-video computation and the need for model-specific compression designs. Extensive experiments across multiple video understanding benchmarks and against diverse compression baselines demonstrate that our approach achieves a strong accuracy-efficiency trade-off, maintaining competitive performance while achieving the lowest inference latency among compared methods.

Related papers

• VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression [52.23010472235226]
  Vision-language models (VLMs) process large numbers of visual tokens, resulting in substantial inference and overhead latency.<n>We propose VisCo, a training-efficient self-compression framework that reuses the pretrained VLM itself as an intrinsic compressor.
  arXiv  Detail & Related papers  (2026-07-14T13:21:36Z)
• ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priors [52.50325804778549]
  We propose ZeroGVC, a zero-shot generative video compression framework.<n>ZeroGVC encodes the first frame of each group of pictures (GOP) with an image and represents subsequent P-frames through Codebook-Guided Autoregressive Latent Compression.<n>Experiments on standard video compression benchmarks demonstrate that ZeroGVC achieves superior perceptual reconstruction quality at ultra-lows without any additional training.
  arXiv  Detail & Related papers  (2026-06-21T07:46:14Z)
• End-to-End Context Compression at Scale [81.70601323130997]
  Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.<n>Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt.<n>Existing approaches are not competitive with KV cache compression on the accuracy-efficiency frontier.
  arXiv  Detail & Related papers  (2026-06-08T15:43:16Z)
• Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention [23.015486635502437]
  Video language models (Video-LLMs) face high computational costs due to large volumes of visual tokens.<n>We propose a unified selection mechanism that weights semantic similarity to globally select tokens.<n>Unselected tokens are merged via clustering and refilled, preserving information integrity.<n>Our unifiedtemporal token compression strategy establishes the state-of-theart in video understanding under ultra-low token retention.
  arXiv  Detail & Related papers  (2026-03-23T13:15:22Z)
• ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling [10.843021248963305]
  We propose a Progressive-based Generative Video Compression framework that unifies progressive transmission, efficient entropy coding, and detail synthesis within a single synthesis.<n>ProGVC encodes videos into hierarchical multi-scale residual token maps, enabling flexible rate adaptation by transmitting a coarse-to-fine subset of scales in a progressive manner.
  arXiv  Detail & Related papers  (2026-03-18T09:51:39Z)
• LoViC: Efficient Long Video Generation with Context Compression [68.22069741704158]
  We introduce LoViC, a DiT-based framework trained on million-scale open-domain videos.<n>At the core of our approach is FlexFormer, an expressive autoencoder that jointly compresses video and text into unified latent representations.
  arXiv  Detail & Related papers  (2025-07-17T09:46:43Z)
• PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models [64.9366388601049]
  Visual token compression is leveraged to reduce the considerable token length of visual inputs.<n>We introduce a unified token compression strategy called Progressive Visual Token Compression.<n>Our model achieves state-of-the-art performance across various video understanding benchmarks.
  arXiv  Detail & Related papers  (2024-12-12T18:59:40Z)
• High-Efficiency Neural Video Compression via Hierarchical Predictive Learning [27.41398149573729]
  Enhanced Deep Hierarchical Video Compression-DHVC 2.0- introduces superior compression performance and impressive complexity efficiency. Uses hierarchical predictive coding to transform each video frame into multiscale representations. Supports transmission-friendly progressive decoding, making it particularly advantageous for networked video applications in the presence of packet loss.
  arXiv  Detail & Related papers  (2024-10-03T15:40:58Z)
• Content Adaptive and Error Propagation Aware Deep Video Compression [110.31693187153084]
  We propose a content adaptive and error propagation aware video compression system. Our method employs a joint training strategy by considering the compression performance of multiple consecutive frames instead of a single frame. Instead of using the hand-crafted coding modes in the traditional compression systems, we design an online encoder updating scheme in our system.
  arXiv  Detail & Related papers  (2020-03-25T09:04:24Z)

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.