DisasterBench is a new multi-stage multimodal reasoning benchmark for UAV disaster response with 14 scenes and 9 tasks; the accompanying 2B DisasterVL model outperforms open-source MLLMs and approaches GPT-4o efficiency.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
ARMS is a learned router for VLM selection trained on a new 32k-query multimodal dataset that outperforms GPT-4o on both in- and out-of-distribution tests after incremental adaptation.
citing papers explorer
-
DisasterBench: A Multimodal Benchmark for UAV-Based Disaster Response in Complex Environments
DisasterBench is a new multi-stage multimodal reasoning benchmark for UAV disaster response with 14 scenes and 9 tasks; the accompanying 2B DisasterVL model outperforms open-source MLLMs and approaches GPT-4o efficiency.
-
An Effective Router for Vision-Language Model Selection
ARMS is a learned router for VLM selection trained on a new 32k-query multimodal dataset that outperforms GPT-4o on both in- and out-of-distribution tests after incremental adaptation.