5 papers
Geometry-aware neural causal discovery for large-scale spatiotemporal systems
Haoyang Yan, Kaiqi Zhao, Weiping Wang +2
Causal discovery at large spatiotemporal scale is difficult: variables are physically embedded, candidate interactions grow quadratically with system size, and causal structure cha…
AnchorGK: Anchor-based Incremental and Stratified Graph Learning Framework for Inductive Spatio-Temporal Kriging
Xiaobin Ren, Kaiqi Zhao, Katerina Taškova +1
Spatio-temporal kriging is a fundamental problem in sensor networks, driven by the sparsity of deployed sensors and the resulting missing observations. Although recent approaches m…
Disentangling Reasoning Logic to Resolve Explicit Knowledge Conflicts
Xianda Zheng, Zijian Huang, Meng-Fen Chiang +4
Explicit knowledge conflicts, occurring when retrieved contexts contain contradictory information, pose a fundamental challenge for Large Language Models (LLMs) as they integrate i…
AdaptGOT: A Pre-trained Model for Adaptive Contextual POI Representation Learning
Xiaobin Ren, Xinyu Zhu, Kaiqi Zhao
Currently, considerable strides have been achieved in Point-of-Interest (POI) embedding methodologies, driven by the emergence of novel POI tasks like recommendation and classifica…
MMS-VPR: A Fine-Grained Multimodal Street-Level Visual Place Recognition Dataset and Evaluation Benchmark for Dense Pedestrian Environments
Yiwei Ou, Xiaobin Ren, Ronggui Sun +3
Existing visual place recognition (VPR) datasets predominantly rely on vehicle-mounted imagery, offer limited multimodal diversity, and underrepresent dense pedestrian street scene…