7 citations · 14 across the 19 of their papers we have counts for
23 papers
The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement
Sijie Zhao, Zeqi Zhou, Heli Qi +6
Earth observation (EO) models are still built by hand. For each new task, experts design a training recipe and tune it against a benchmark. We show that this loop can be handed to…
DenMark: Robust Semantic Watermarking for Diffusion Language Models
Tianhao Ma, Weihao Xuan, Dong-Dong Wu +5
Semantic text watermarks encode signals in meaning rather than surface token choices, offering robustness to paraphrasing and other semantic-preserving edits. Existing semantic wat…
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…
MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photos
Leyuan Yu, Xiao Tang, Minghao Liu +6
Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input. Existing what-if tasks typically v…
OpenEarth-Agent: From Tool Calling to Tool Creation for Open-Environment Earth Observation
Sijie Zhao, Feng Liu, Xueliang Zhang +11
Earth Observation (EO) is essential for perceiving dynamic land surface changes, yet deploying autonomous EO in open environments is hindered by the immense diversity of multi-sour…
Direction-aware 3D Large Multimodal Models
Quan Liu, Weihao Xuan, Junjue Wang +3
3D large multimodal models (3D LMMs) rely heavily on ego poses for enabling directional question-answering and spatial reasoning. However, most existing point cloud benchmarks cont…
Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth Observers
Pengyu Dai, Weihao Xuan, Junjue Wang +4
Recent advances have enabled large language model (LLM) agents to solve complex tasks by orchestrating external tools. However, these agents often struggle in specialized, tool-int…
The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents
Weihao Xuan, Qingcheng Zeng, Heli Qi +3
Autonomous agents based on large language models (LLMs) are rapidly evolving to handle multi-turn tasks, but ensuring their trustworthiness remains a critical challenge. A fundamen…
Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagery
Mai Tsujimoto, Junjue Wang, Weihao Xuan +1
Three-dimensional geospatial analysis is critical for applications in urban planning, climate adaptation, and environmental assessment. However, current methodologies depend on cos…
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
Fang Wu, Weihao Xuan, Heli Qi +4
Although RLVR has become an essential component for developing advanced reasoning skills in language models, contemporary studies have documented training plateaus after thousands…
Multiplayer Nash Preference Optimization
Fang Wu, Xu Huang, Weihao Xuan +8
Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models with human preferences. However, reward-based methods grou…
The Invisible Leash: Why RLVR May or May Not Escape Its Origin
Fang Wu, Weihao Xuan, Danny Xing +5
Recent advances highlight Reinforcement Learning with Verifiable Rewards (RLVR) as a promising approach to enhancing LLM capabilities. However, it remains unclear whether the curre…
Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models
Weihao Xuan, Qingcheng Zeng, Heli Qi +2
Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models expr…
DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response
Junjue Wang, Weihao Xuan, Heli Qi +8
Large vision-language models (VLMs) have made great achievements in Earth vision. However, complex disaster scenes with diverse disaster types, geographic regions, and satellite se…
DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding
Weihao Xuan, Junjue Wang, Heli Qi +5
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in visual understanding, but their application to long-term Earth observation analysis remains li…
Is Pre-training Applicable to the Decoder for Dense Prediction?
Chao Ning, Wanshui Gan, Weihao Xuan +1
Pre-trained encoders are widely employed in dense prediction tasks for their capability to effectively extract visual features from images. The decoder subsequently processes these…
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation
Weihao Xuan, Rui Yang, Heli Qi +29
Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingui…
BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response
Hongruixuan Chen, Jian Song, Olivier Dietrich +9
Disaster events occur around the world and cause significant damage to human life and property. Earth observation (EO) data enables rapid and comprehensive building damage assessme…
Foundation Models for Remote Sensing and Earth Observation: A Survey
Aoran Xiao, Weihao Xuan, Junjue Wang +4
Remote Sensing (RS) is a crucial technology for observing, monitoring, and interpreting our planet, with broad applications across geoscience, economics, humanitarian fields, etc.…
Segment Anything with Multiple Modalities
Aoran Xiao, Weihao Xuan, Heli Qi +3
Robust and accurate segmentation of scenes has become one core functionality in various visual recognition and navigation tasks. This has inspired the recent development of Segment…
SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery
Jian Song, Hongruixuan Chen, Weihao Xuan +2
Global semantic 3D understanding from single-view high-resolution remote sensing (RS) imagery is crucial for Earth Observation (EO). However, this task faces significant challenges…
CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model
Aoran Xiao, Weihao Xuan, Heli Qi +5
The recent Segment Anything Model (SAM) has demonstrated remarkable zero-shot capability and flexible geometric prompting in general image segmentation. However, SAM often struggle…
3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds
Aoran Xiao, Jiaxing Huang, Weihao Xuan +6
Robust point cloud parsing under all-weather conditions is crucial to level-5 autonomy in autonomous driving. However, how to learn a universal 3D semantic segmentation (3DSS) mode…