Metraipolis › archive › dc_3bbddf89a298
WaveLLM: Wavelet-Domain LLM Entropy Modeling for Lossless Image Compression — arXiv:2610.22232
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22232
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:36:48.720Z
- SHA-256 of the archived text
29917e19fe683ec505ed1a506d20bd8ecc87fd7e64f9fbe5546d401c83f0eb6b- Stable URL of this page
https://metraipolis.com/documento/dc_3bbddf89a298
How to cite
WaveLLM: Wavelet-Domain LLM Entropy Modeling for Lossless Image Compression — arXiv:2610.22232 — arXiv (en), https://arxiv.org/abs/2610.22232 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3bbddf89a298 (Metraipolis archive dc_3bbddf89a298, sha256 29917e19fe683ec505ed1a506d20bd8ecc87fd7e64f9fbe5546d401c83f0eb6b)
BibTeX
@misc{dc3bbddf89a298,
title = {WaveLLM: Wavelet-Domain LLM Entropy Modeling for Lossless Image Compression — arXiv:2610.22232},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22232},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3bbddf89a298; sha256 29917e19fe683ec505ed1a506d20bd8ecc87fd7e64f9fbe5546d401c83f0eb6b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22232. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Lossless image compression fundamentally relies on accurate entropy modeling, driving a recent shift toward large language model (LLM)-based methods. However, existing approaches mainly emphasize the modeling capacity of LLMs while directly serializing images into pixel or residual sequences, leaving heterogeneous signal patterns entangled within a single prediction stream. In this paper, we argue that effective entropy modeling depends not only on model capacity, but also on the predictability of the input representation. Motivated by this insight, we propose WaveLLM, a wavelet-domain LLM-based entropy model for lossless image compression. By decomposing an image into multi-level wavelet subbands, WaveLLM converts a heterogeneous prediction problem into a set of more structured and statistically homogeneous subproblems that are more amenable to autoregressive probability estimation. To bridge numerical coding symbols with the LLM's native text token space, we introduce a dedicated numerical interface featuring value embeddings and a coefficient prediction head. Furthermore, a task-adaptive prompting strategy is designed to enable a single shared model to adapt to diverse subbands within a unified framework. Built on Llama-3.2-3B with LoRA adaptation, WaveLLM achieves 2.51, 2.24, and 2.27 bpsp on Kodak, this http URL , and DIV2K, respectively, outperforming the PixelCNN-based codec using the same wavelet transform by 0.43, 0.36, and 0.46 bpsp, and surpassing recent LLM-based lossless compressors on all three benchmarks. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.22232 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:52:02.724Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).