aiqbench analysis
This research introduces MODL, a novel training recipe that enables Remote-Sensing Multimodal Large Language Models (MLLMs) to acquire new languages without any paired multimodal data. By enforcing mutual orthogonality between domain-specific and language-specific Low-Rank Adaptation (LoRA) updates, the method successfully preserves existing multilingual capabilities while achieving significant accuracy improvements over standard merging techniques. The approach effectively addresses a critical bottleneck in making specialized vision-language models accessible across diverse linguistic contexts using only text-only instruction data for new languages.
One Domain, Many Tongues: Composing Domain and Language LoRAs for Cross-Lingual Remote-Sensing MLLMs without Paired Data
arXiv:2609.26097v1 Announce Type: cross Abstract: 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.
Abstract: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.
Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2609.26097 [cs.CL]
(or arXiv:2609.26097v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.26097 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 304 words
Related coverage
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · Jun 12, 2026
The Entangled Dimensions of Decision Theory
LessWrong · Jul 30, 2026
From Data to Dialogue: How S&P Global Energy Made Its Structured Data Estate Conversational with Databricks Genie Agents and MCP
Databricks · Sep 25, 2026
Amazon is investing in the Lean Focused Research Organization
Amazon Science · Jul 26, 2026