PaperScope
LIVE · 2026-09-29 05:40 UTC

Gradient-Guided Decoupled Adaptation for Geospatial Vision-Language Models

Dongdong Wang, Deepak Balakrishnan, Ravi Srinivasan, Shenhao Wang

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.32737 v1
Submitted
2026-09-26

Abstract

Existing geospatial vision-language models (Geo-VLMs) typically optimize diverse geospatial tasks through a unified multi-task adaptation paradigm without explicitly accounting for the heterogeneous optimization characteristics. Our empirical observations reveal heterogeneous gradient characteristics across tasks, including vision-language differences, intra-branch gradient relationships, and task interference, which hinder effective multi-task optimization. Motivated by these observations, we propose Gradient-Guided Decoupled Adaptation (G2DA), a gradient-aware optimization framework for multi-task Geo-VLM learning. G2DA first partitions tasks into vision- and language-centric groups through gradient-guided cross-modal decoupling. It then constructs modality-specific curricula based on task gradient similarity and employs bidirectional rehearsal to mitigate the recency effects introduced by sequential optimization. We evaluate G2DA on three Geo-VLM benchmarks using six InternVL3 and Qwen3.5-VL variants, along with GeoChat and GeoLLaVA. Across all 24 benchmark-model combinations, G2DA consistently outperforms representative baselines, improving over the strongest competitor by 3.08, 4.30, and 2.81 percentage points on UrBench-MCQ, XLRS-Bench-Lite, and VRS-Bench-VQA, respectively. These results demonstrate the effectiveness of gradient-guided task organization for Geo-VLM adaptation.

Comment: 8 pages, 3 figures, 4 tables

arXiv abs page · PDF · same-day batch