Metraipolis › archive › dc_ccc1122cafa6

One Domain, Many Tongues: Composing Domain and Language LoRAs for Cross-Lingual Remote-Sensing MLLMs without Paired Data — arXiv:2609.26097

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26097
License (as archived)
CC0-1.0
Archived
2026-10-08T14:36:37.509Z
SHA-256 of the archived text
5f315975d30e3c91e294a7c39b8964b1793da52cf2120addb5cf9f4b58ac5326
Stable URL of this page
https://metraipolis.com/documento/dc_ccc1122cafa6

How to cite

One Domain, Many Tongues: Composing Domain and Language LoRAs for Cross-Lingual Remote-Sensing MLLMs without Paired Data — arXiv:2609.26097 — arXiv (en), https://arxiv.org/abs/2609.26097 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccc1122cafa6 (Metraipolis archive dc_ccc1122cafa6, sha256 5f315975d30e3c91e294a7c39b8964b1793da52cf2120addb5cf9f4b58ac5326)
BibTeX
@misc{dcccc1122cafa6,
  title = {One Domain, Many Tongues: Composing Domain and Language LoRAs for Cross-Lingual Remote-Sensing MLLMs without Paired Data — arXiv:2609.26097},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26097},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccc1122cafa6; sha256 5f315975d30e3c91e294a7c39b8964b1793da52cf2120addb5cf9f4b58ac5326},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26097. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Remote-sensing (RS) multimodal large language models (MLLMs) are trained and evaluated only in English, while text-only instruction data covers over 100 languages. We propose MODL (Mutually Orthogonal Domain-Language composition), a recipe that adds new languages to an English RS MLLM without a single multilingual RS example: a domain LoRA trained on English RS imagery and a language LoRA trained on text alone are learned jointly, under one loss term that keeps the two updates mutually orthogonal at every layer throughout training. This constraint is the recipe's active ingredient. Without it, the same training answers RS questions correctly but in English, erases much of the base model's multilingual text ability, and diverges on one seed in three; sixteen alternatives, from training-free merging to prior orthogonality variants, fail the same way. MODL repairs every failure on every seed: answers are correct and in the target language 56-71% of the time, where the best alternative reaches 27% and most stay below 8%, text ability stays at the level of the untrained base, and on Spanish it surpasses Qwen2.5-VL-7B, with zero multilingual-multimodal data. A single five-language adapter retains English, Spanish, and Vietnamese at full strength across three seeds; non-Latin scripts remain an open boundary.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.26097 — 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 2026-10-08T13:46:15.718Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).