SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.22286 · 2026

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

Qi Wang, Yan Zhao, Li Song, Dajiang Zhou, Zhengxue Cheng, Junxuan Zhang, 𝒙 𝟏, Qunshan Gu, < 𝒊𝒎𝒂𝒈𝒆 >, 𝑳 𝟑, < 𝒕𝒂𝒄𝒕𝒊𝒍𝒆 >, 𝒚 𝟏, and 2 more

arXiv · PDF · Open in the Atlas

Code that ran

5 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 8 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.22286.json · badge: /api/ran/2602.22286.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
adminasmi/OmniZip-CVPR2026 community
Papers with Code archive
5 ran · 8 no recorded run
FunctionStatusWhere it lives
AttnBlkHiRA Ran
ran on a synthesized input · constructed an object; no result was computed
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("149772ae5e8b0d5a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

MLP Ran
ran on a synthesized input · constructed an object; no result was computed
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("bda257f078dbbab8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

RMSNorm Ran
ran on a synthesized input · constructed an object; no result was computed
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("c1ff30fd8e32c15e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

expert_balance_jit Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("4ad12fdafbefb97b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gates_to_load_jit Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("99695f198331261b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

BaseBlockMoAMoE Not yet run
unverified (harvested, no recorded run)
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("6f658e386bcf4fa5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

BaseRWKV_HIRA_MOA_MOE Not yet run
unverified (harvested, no recorded run)
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("00ae33db75447388")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

ExpertRouter Not yet run
unverified (harvested, no recorded run)
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("bcca08dbafa1bf18")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

MoE Not yet run
unverified (harvested, no recorded run)
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("5e190de60aac899d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

_log_expert_stats Not yet run
unverified (harvested, no recorded run)
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("62250fc6b0cb47f9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

_plot_expert_usage Not yet run
unverified (harvested, no recorded run)
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("ed91c0888857ce4d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

cv_squared_jit Not yet run
unverified (harvested, no recorded run)
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("1bf0709d8a84d473")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

prob_in_top_k_jit Not yet run
unverified (harvested, no recorded run)
adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py
pointer only (licence: NONE) · get_code("a55a7c552eac18c2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adminasmi/OmniZip-CVPR2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 13 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.22286")
get_code_for_paper("2602.22286")
have("2602.22286")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.22286.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.22286.svg)](https://syntology.ai/paper/2602.22286)

Connect an agent — have() is free.