17 papers
Driver2Map: Imitating Human Driving for Online High-Definition Map Construction
Pan Yin, Runtian Xia, Weisong Kuang +3
High-definition (HD) maps are essential for autonomous driving systems. In constructing such maps, onboard multi-view camera images, standard-definition maps and satellite images p…
OVEarth-Bench: Evaluating Category Breadth and Query Diversity for Open-Vocabulary Earth Observation
Kaiyu Li, Zepeng Xin, Zixuan Jiang +4
The paper presents OVEarth-Bench, a new benchmark for open-vocabulary Earth observation that evaluates models on a wide hierarchical set of categories and diverse query types, supp…
CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming
Ruixun Liu, Lingyu Zhang, Lanxuan Xue +3
Humans can effortlessly reason about scenes across different viewpoints, yet it remains unclear whether Vision-Language Models (VLMs) possess similar cross-view spatial abilities.…
Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle
Jiayu Wang, Weijiang Lv, Bowen Fu +8
As foundation models advance and agent scaffolding becomes increasingly sophisticated, agents have demonstrated remarkable proficiency in complex, long-horizon coding tasks and eve…
SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images
Kaiyu Li, Shengqi Zhang, Yujie Wang +4
Most existing methods for training-free open-vocabulary semantic segmentation are based on CLIP. While these approaches have made progress, they often face challenges in precise lo…
Multi-Modal Building Change Detection for Large-Scale Small Changes: Benchmark and Baseline
Ye Wang, Wei Lu, Zhihui You +6
Change detection in optical remote sensing imagery is susceptible to illumination fluctuations, seasonal changes, and variations in surface land-cover materials. Relying solely on…