One Domain, Many Tongues: Composing Domain and Language LoRAs for Cross-Lingual Remote-Sensing MLLMs without Paired Data
cs.CL, cs.CV, cs.LG
Submitted: 2026-08-04
Updated: 2026-08-04
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- No Language Left Behind: Scaling Human-Centered Machine Translation
- Model Merging via Multi-Teacher Knowledge Distillation
- Aya Vision: Advancing the Frontier of Multilingual Multimodality
- Editing Models with Task Arithmetic
- Dataless Knowledge Fusion by Merging Weights of Language Models
- Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation
- DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation
- Multilingual Training-Free Remote Sensing Image Captioning
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
- Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropout
- Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging
- A Benchmark for Multi-Lingual Vision-Language Learning in Remote Sensing Image Captioning
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering