一个轻量级统一压缩器，能高效压缩图像、文本、语音等多模态数据。
OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data
- 用统一分词器和路由机制，让不同数据类型共享同一压缩模型。
- 在多个数据集上压缩效率比gzip高42%至62%，且支持实时推理。
- 适合边缘设备部署，手机CPU也能达1MB/s压缩速度。
无损压缩对高效存储和传输至关重要。尽管基于学习的压缩器表现优异，但多数仅针对单一模态，导致多模态场景下需部署多个压缩器。设计统一的多模态压缩器虽关键却困难，因不同数据格式、维度和统计特性差异大。多模态大模型虽有潜力，但过于复杂难以实用。为此，我们提出OmniZip——一个面向多模态数据（如图像、文本、语音、触觉、数据库、基因序列）的统一且轻量的无损压缩器。基于轻量骨干网络，OmniZip包含三个核心组件：可逆转换多种数据为令牌的统一分词器、支持灵活多模态上下文建模的路由机制，以及增强非线性表达能力的路由前馈设计。采用重参数化训练策略提升模型容量。OmniZip在多个模态上优于或匹配现有最优压缩器，在CLIC-M、TouchandGo、enwik9、LibriSpeech和WikiSQL数据集上分别比gzip提升42%、57%、62%、42%和53%的压缩效率。同时支持资源受限边缘设备上的近实时推理，于MacBook CPU上达到约1MB/s，iPhone NPU上亦可实现。代码已开源：https://github.com/adminasmi/OmniZip-CVPR2026。
原文摘要 · Abstract (English)
Lossless compression is essential for efficient data storage and transmission. Although learning-based lossless compressors achieve strong results, most of them are designed for a single modality, leading to redundant compressor deployments in multi-modal settings. Designing a unified multi-modal compressor is critical yet challenging, as different data types vary largely in format, dimension, and statistics. Multi-modal large language models offer a promising resolution but remain too complex for practical use. Thus, we propose \textbf{OmniZip}, \textbf{a unified and lightweight lossless compressor for multi-modal data (like image, text, speech, tactile, database, and gene sequence)}. Built on a lightweight backbone, OmniZip incorporates three key components to enable efficient multi-modal lossless compression: a modality-unified tokenizer that reversibly transforms diverse data into tokens, a modality-routing context learning mechanism that enables flexible multi-modal context modeling, and a modality-routing feedforward design that further enhances the model's nonlinear representation flexibility. A reparameterization training strategy is used to enhance model capacity. OmniZip outperforms or matches other state-of-the-art compressors on multiple modalities, achieving 42\%, 57\%, 62\% and 42\%, 53\% higher compression efficiency than gzip on CLIC-M, TouchandGo, enwik9, LibriSpeech, and WikiSQL datasets, respectively. It also supports near real-time inference on resource-constrained edge devices, reaching about 1MB/s on MacBook CPUs and iPhone NPUs. Our code is released at https://github.com/adminasmi/OmniZip-CVPR2026.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。