21 papers
DIAL: Dynamic and Informed Adjustment of the Native Stochastic Law for Reliable Weather Ensembles
Yucheng Wang, Haonan Guo, Tianhao Zhao +4
Ensemble weather forecasts can look reliable in global averages while hiding too little spread in some cases and too much in others. These errors vary across variables, spatial sca…
ReDiS: Reasoning-Diagnosis Self-Evolution for Multimodal Reasoning in Remote Sensing
Yi Liu, Wentao Jiang, Shuo Ni +5
Multimodal large language models (MLLMs) have shown strong potential for remote sensing understanding, yet reliable reasoning remains challenging when tasks require fine-grained vi…
Hallucination-aware Faithful Reasoning in Remote Sensing
Yi Liu, Jing Zhang, Xiang Feng +5
Multimodal large language models (MLLMs) have demonstrated promising capabilities for remote sensing reasoning, yet they frequently generate visually unsupported reasoning that con…
OmniRSI: Taming Latent Diffusion for Unified Multimodal Remote Sensing Image Generation
Hebaixu Wang, Jing Zhang, Haonan Guo +3
Multimodal remote sensing image generation emerges as a promising paradigm for recovering complete and complementary observations from heterogeneous and partially observed remote s…
RSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language Models
Dongchen Si, Di Wang, Mingzhen Xu +3
Remote sensing scene classification is a fundamental task in Earth observation and geospatial analysis. Existing approaches mainly follow three paradigms: task-specific visual clas…
SAMe: A Semantic Anatomy Mapping Engine for Robotic Ultrasound
Jing Zhang, Duojie Chen, Wentao Jiang +7
Robotic ultrasound has advanced local image-driven control, contact regulation, and view optimization, yet current systems lack the anatomical understanding needed to determine wha…
Echo-α: Large Agentic Multimodal Reasoning Model for Ultrasound Interpretation
Jing Zhang, Wentao Jiang, Tao Huang +8
Ultrasound interpretation requires both precise lesion localization and holistic clinical reasoning, yet existing methods typically excel at only one of these capabilities: special…
Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing
Yi Liu, Jing Zhang, Di Wang +3
Multimodal large language models (MLLMs) suffer from pronounced hallucinations in remote sensing visual question-answering (RS-VQA), primarily caused by visual grounding failures i…
Any2Any: Unified Arbitrary Modality Translation for Remote Sensing
Haoyang Chen, Jing Zhang, Hebaixu Wang +7
Multi-modal remote sensing imagery provides complementary observations of the same geographic scene, yet such observations are frequently incomplete in practice. Existing cross-mod…
Universal Pansharpening Model
Hebaixu Wang, Jing Zhang, Haonan Guo +4
Pansharpening generates the high-resolution multi-spectral (MS) image by integrating spatial details from a texture-rich panchromatic (PAN) image and spectral attributes from a low…
GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery
Fengxiang Wang, Mingshuo Chen, Yueying Li +10
The "thinking-with-images" paradigm enables multimodal large language models (MLLMs) to actively explore visual scenes via zoom-in tools. This is essential for ultra-high-resolutio…
Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding
Fengxiang Wang, Mingshuo Chen, Yueying Li +13
Multimodal reasoning for ultra-high-resolution (UHR) remote sensing (RS) is usually bottlenecked by visual evidence acquisition: the model necessitates localizing tiny task-relevan…
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…
QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning
Tianran Ouyang, Xingping Dong, Jing Zhang +4
Slot Attention, an approach that binds different objects in a scene to a set of "slots", has become a leading method in unsupervised object-centric learning. Most methods assume a…
GeoBridge++: Fact-Guided Geo-Semantic Bridging for Unified Cross-View Geo-Localization
Zixuan Song, Jing Zhang, Di Wang +7
Cross-view geo-localization infers a location by retrieving geo-tagged reference images matching a query image. However, the traditional satellite-centric paradigm limits robustnes…
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…
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…
SPEX: A Vision-Language Model for Land Cover Extraction on Spectral Remote Sensing Images
Dongchen Si, Di Wang, Erzhong Gao +9
Spectral information has long been recognized as a critical cue in remote sensing observations. Although numerous vision-language models have been developed for pixel-level interpr…
TiMo: Spatiotemporal Foundation Model for Satellite Image Time Series
Xiaolei Qin, Di Wang, Jing Zhang +4
Satellite image time series (SITS) provide continuous observations of the Earth's surface, making them essential for applications such as environmental management and disaster asse…
DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration
Hebaixu Wang, Jing Zhang, Haonan Guo +3
Diffusion models have achieved remarkable progress in universal image restoration. While existing methods speed up inference by reducing sampling steps, substantial step intervals…
GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
Fengxiang Wang, Mingshuo Chen, Yueying Li +11
Ultra-high-resolution (UHR) remote sensing (RS) imagery offers valuable data for Earth observation but pose challenges for existing multimodal foundation models due to two key bott…