Metraipolis › archive › dc_64ee5403ab45
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models — arXiv:2608.03812
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03812
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:59:48.486Z
- SHA-256 of the archived text
cabc34a3fd0aac7fb2c07eb5adff82018e8ede6d12a491ff2a242d2df3240cd1- Stable URL of this page
https://metraipolis.com/documento/dc_64ee5403ab45
How to cite
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models — arXiv:2608.03812 — arXiv (en), https://arxiv.org/abs/2608.03812 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_64ee5403ab45 (Metraipolis archive dc_64ee5403ab45, sha256 cabc34a3fd0aac7fb2c07eb5adff82018e8ede6d12a491ff2a242d2df3240cd1)
BibTeX
@misc{dc64ee5403ab45,
title = {OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models — arXiv:2608.03812},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03812},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_64ee5403ab45; sha256 cabc34a3fd0aac7fb2c07eb5adff82018e8ede6d12a491ff2a242d2df3240cd1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03812. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Omni-modal large language models (Omni-LLMs) have achieved remarkable performance on audio-visual understanding tasks, but processing long and highly redundant visual and audio token sequences incurs substantial computational overhead, demanding aggressive token compression for efficient deployment. Existing methods often degrade at low token budgets: pre-LLM compression may discard structurally important and globally distributed evidence, whereas inner-LLM compression often underexploits query-conditioned audio-visual collaboration. To address these limitations, we propose OmniPack, a training-free framework that coordinates structural compression before the LLM with task-relevant semantic refinement within the LLM. Before the LLM, OmniPack removes structural redundancy through modality-specific importance, global coverage, and similarity-aware merging. After sufficient multimodal interaction, it further consolidates diverse, task-relevant representations through textual guidance and audio-visual collaboration. Extensive experiments on five benchmarks with three Omni-LLM backbones demonstrate that OmniPack consistently achieves the best performance-efficiency trade-off across diverse retention ratios, outperforming all existing methods. Notably, on Qwen2.5-Omni-7B, OmniPack preserves 98.0% of the original performance while reducing FLOPs to 16.7%, and still retains 92.9% of the original performance with only 6.8% of the original FLOPs. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.03812 — 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 2026-10-31T12:45:33.277Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).