3 papers
cs.CV2026
DIVE: Dynamic Iterative Visual Evidence Construction for Efficient Vision-Language Models
Chen Zhong, Xiao An, Zijie Wang +3
Visual inputs in vision-language models (VLMs) are often encoded into substantially longer token sequences than text, making visual tokens a major bottleneck for efficient inferenc…
cs.CV2026
Advancing All-Weather Building Damage Mapping to the Instance Level: Outcomes and Insights from the 2026 Bright Challenge
Hongruixuan Chen, He Huang, Haifeng Wang +19
Rapid post-disaster response requires timely, building-level information on whether structures remain intact, are damaged, or are destroyed. Post-event optical imagery, however, ma…
cs.CV2025
Building-Guided Pseudo-Label Learning for Cross-Modal Building Damage Mapping
Jiepan Li, He Huang, Yu Sheng +2
Accurate building damage assessment using bi-temporal multi-modal remote sensing images is essential for effective disaster response and recovery planning. This study proposes a no…