Metraipolis › archive › dc_dea92ec635b9
UniFed-VLM: Federated Instruction Tuning for Vision-Language Models with Multiple Heterogeneity — arXiv:2608.15516
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15516
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:40:36.984Z
- SHA-256 of the archived text
8c8185dbf81b7e67ba36523fad0d84e4f59487219c2b1cb1761d59c518bb47a0- Stable URL of this page
https://metraipolis.com/documento/dc_dea92ec635b9
How to cite
UniFed-VLM: Federated Instruction Tuning for Vision-Language Models with Multiple Heterogeneity — arXiv:2608.15516 — arXiv (en), https://arxiv.org/abs/2608.15516 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dea92ec635b9 (Metraipolis archive dc_dea92ec635b9, sha256 8c8185dbf81b7e67ba36523fad0d84e4f59487219c2b1cb1761d59c518bb47a0)
BibTeX
@misc{dcdea92ec635b9,
title = {UniFed-VLM: Federated Instruction Tuning for Vision-Language Models with Multiple Heterogeneity — arXiv:2608.15516},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15516},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dea92ec635b9; sha256 8c8185dbf81b7e67ba36523fad0d84e4f59487219c2b1cb1761d59c518bb47a0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15516. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language Models (VLMs) have demonstrated strong performance in multimodal understanding and generation. However, fine-tuning of VLMs typically relies on centralized data, which raises privacy concerns in certain domains (e.g. healthcare). Federated Learning (FL) provides a natural solution by enabling model training without sharing raw data. However, applying FL to VLM instruction tuning is highly challenging. VLMs have substantial parameter scales, and in real-world scenarios, clients exhibit significant heterogeneity in tasks, modalities, and model architectures. Existing methods mainly focus on simplified settings and are unable to handle such multi-dimensional heterogeneous scenarios. In this work, we study federated instruction tuning under joint heterogeneity in tasks, modalities, and model architectures. We propose UniFed-VLM, a unified federated instruction tuning framework for VLMs that addresses multiple types of heterogeneity. It consists of two key components: 1) Federated Compensated Subspace Aggregation (FedCSA), which performs subspace-aligned aggregation of parameter-efficient adapters with dynamic weighting and compensation to mitigate heterogeneity-induced conflicts; 2) Two-stage Collaborative Distillation (TCoD), which enables effective knowledge transfer across heterogeneous models via a Mutual Distillation Adapter (MDA) and a mixture-of-experts-based distillation strategy. We conduct experiments on multiple benchmark datasets, and the results show that UniFed-VLM achieves stronger average performance across diverse tasks compared with existing FL methods. The source code is available at: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.15516 — 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 2026-10-18T19:02:44.104Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).