# OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data

arXiv: https://arxiv.org/abs/2602.22286 · HTML: https://mlsanity.com/paper/2602.22286/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 69 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 30 of 31)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [RWKV-7 "Goose" with Expressive Dynamic State Evolution](https://mlsanity.com/paper/2503.14456/) (2025)
- [Practical Full Resolution Learned Lossless Image Compression](https://mlsanity.com/paper/1811.12817/) (2018)
- [A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization](https://mlsanity.com/paper/1902.01069/) (2019)
- [Touch and Go: Learning from Human-Collected Vision and Touch](https://mlsanity.com/paper/2211.12498/) (2022)
- [ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations](https://mlsanity.com/paper/2109.07991/) (2021)
- [LLMZip: Lossless Text Compression using Large Language Models](https://mlsanity.com/paper/2306.04050/) (2023)
- [FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec](https://mlsanity.com/paper/2309.07405/) (2023)
- [Learning Better Lossless Compression Using Lossy Compression](https://mlsanity.com/paper/2003.10184/) (2020)
- [iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression](https://mlsanity.com/paper/2103.16211/) (2021)
- [iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder](https://mlsanity.com/paper/2111.00965/) (2021)
- [Linear Attention Modeling for Learned Image Compression](https://mlsanity.com/paper/2502.05741/) (2025)
- [Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression](https://mlsanity.com/paper/2209.04847/) (2022)
- [FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression](https://mlsanity.com/paper/2409.17141/) (2024)
- [Large Language Model for Lossless Image Compression with Visual Prompts](https://mlsanity.com/paper/2502.16163/) (2025)
- [Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data](https://mlsanity.com/paper/2410.05078/) (2024)
- [aiWave: Volumetric Image Compression with 3-D Trained Affine Wavelet-like Transform](https://mlsanity.com/paper/2203.05822/) (2022)
- [Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need](https://mlsanity.com/paper/2411.12448/) (2024)
- [L3TC: Leveraging RWKV for Learned Lossless Low-Complexity Text Compression](https://mlsanity.com/paper/2412.16642/) (2024)
- [DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor](https://mlsanity.com/paper/2505.16256/) (2025)
- [TaCo: A Benchmark for Lossless and Lossy Codecs of Heterogeneous Tactile Data](https://mlsanity.com/paper/2602.09893/) (2026)
- [Rate-Aware Learned Speech Compression](https://mlsanity.com/paper/2501.11999/) (2025)

## Built on by (most cited first, 2 of 2)

- [OmniDrop: Layer-wise Token Pruning for Omni-modal LLMs via Query-Guidance](https://mlsanity.com/paper/2605.14458/) (2026)
- [HyperZip: Efficient Data Compression through Personalized Diffusion LLMs with Hypernetworks](https://mlsanity.com/paper/2609.36357/) (2026)

## Abstract (arXiv)

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 OmniZip, 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.