Model Releases
Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs
arXiv:2607.22205v1 Announce Type: new Abstract: Remote sensing multimodal large language models (RS-MLLMs) have improved general aerial-image understanding. However, Earth observation applications req
arXiv:2607.22205v1 Announce Type: new Abstract: Remote sensing multimodal large language models (RS-MLLMs) have improved general aerial-image understanding. However, Earth observation applications require fine-grained scenario specialization, constrained by scarce high-quality scenario data and incomplete capability coverage. We formulate this adaptation as a capability-gap-driven post-training problem and propose filling before advancing (FBA). Rather than relying on single-stage supervised fine-tuning (SFT) over target-domain samples, FBA first fills prerequisite capability gaps before advancing toward scenario specialization. We instantiate FBA for coastal harbor understanding, a representative multi-source scenario, by constructing CPRS (Coastal-Port Remote Sensing), a three-layer supervision dataset coupled with three ordered stages: (1) RS semantic anchoring for overhead-view visual-language alignment; (2) domain-bridge convergence for shared RS priors across target and bridging scenarios under different modalities; and (3) evidence-grounded scenario tuning for downstream performance. We construct HarborEval, an eight-track diagnostic benchmark covering perception, spatial understanding, robustness, and generation. Under comparable training budgets, HarborEval increases from 57.95 with Direct-SFT to 70.29 with FBA on LLaVA-v1.5, and from 81.09 to 83.37 on Qwen3-VL. FBA also outperforms Collapsed-SFT and leads on harbor-related VRSBench/RSVQA subsets and OpenEval. Stage-wise and role-replacement analyses validate progressive gap filling and stage-specific roles. Public examples and release updates for CPRS, HarborEval, code, and trained weights are available at https://github.com/Z0ngL1ng/filling-before-advancing.
Related
- Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models
- Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding
- Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs
- GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision
- Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks
Source: arXiv cs.CV | 2026-07-27