8 papers
VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing
Zhiming Luo, Di Wang, Haonan Guo +2
Recent advancements in Multimodal Large Language Models (MLLMs) have enabled complex reasoning. However, existing remote sensing (RS) benchmarks remain heavily biased toward percep…
UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes
Shuo Ni, Di Wang, He Chen +3
Instruction-driven segmentation in remote sensing generates masks from guidance, offering great potential for accessible and generalizable applications. However, existing methods s…
Residual Diffusion Bridge Model for Image Restoration
Hebaixu Wang, Jing Zhang, Haoyang Chen +4
Diffusion bridge models establish probabilistic paths between arbitrary paired distributions and exhibit great potential for universal image restoration. Most existing methods mere…
GeoBridge: A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text for Geo-Localization
Zixuan Song, Jing Zhang, Di Wang +5
Cross-view geo-localization infers a location by retrieving geo-tagged reference images that visually correspond to a query image. However, the traditional satellite-centric paradi…
GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes
Di Wang, Shunyu Liu, Wentao Jiang +10
Multimodal large language models (MLLMs) have undergone rapid development in advancing geospatial scene understanding. Recent studies have sought to enhance the reasoning capabilit…
Intra-Trajectory Consistency for Reward Modeling
Chaoyang Zhou, Shunyu Liu, Zengmao Wang +4
Reward models are critical for improving large language models (LLMs), particularly in reinforcement learning from human feedback (RLHF) or inference-time verification. Current rew…