1 code implementation • 17 May 2025 • Zhangyu Wang, Siyuan Gao, Rong Zhou, Hao Wang, Li Ning
Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks.
no code implementations • 23 Mar 2025 • Zhangyu Wang, Jielu Zhang, Zhongliang Zhou, Qian Cao, Nemin Wu, Zeping Liu, Lan Mu, Yang song, Yiqun Xie, Ni Lao, Gengchen Mai
To avoid the problematic manifold reprojection step in diffusion, we developed a novel spherical positional encoding-decoding framework, which encodes points on a spherical surface (e. g., geolocations on Earth) into a Hilbert space of Spherical Harmonics coefficients and decodes points (geolocations) by mode-seeking.
no code implementations • 18 Oct 2024 • Shirly Stephen, Mitchell Faulk, Krzysztof Janowicz, Colby Fisher, Thomas Thelen, Rui Zhu, Pascal Hitzler, Cogan Shimizu, Kitty Currier, Mark Schildhauer, Dean Rehberger, Zhangyu Wang, Antrea Christou
Geospatial Knowledge Graphs (GeoKGs) have become integral to the growing field of Geospatial Artificial Intelligence.
no code implementations • 17 Oct 2024 • Cogan Shimizu, Shirly Stephe, Adrita Barua, Ling Cai, Antrea Christou, Kitty Currier, Abhilekha Dalal, Colby K. Fisher, Pascal Hitzler, Krzysztof Janowicz, Wenwen Li, Zilong Liu, Mohammad Saeid Mahdavinejad, Gengchen Mai, Dean Rehberger, Mark Schildhauer, Meilin Shi, Sanaz Saki Norouzi, Yuanyuan Tian, Sizhe Wang, Zhangyu Wang, Joseph Zalewski, Lu Zhou, Rui Zhu
KnowWhereGraph is one of the largest fully publicly available geospatial knowledge graphs.
no code implementations • ICLR Workshop GTRL 2021 • Zhangyu Wang, Lantian Xu, Zhifeng Kong, Weilong Wang, Xuyu Peng, Enyang Zheng
Hyperbolic embeddings are a class of representation learning methods that offer competitive performances when data can be abstracted as a tree-like graph.
2 code implementations • 21 Jun 2024 • Nemin Wu, Qian Cao, Zhangyu Wang, Zeping Liu, Yanlin Qi, Jielu Zhang, Joshua Ni, Xiaobai Yao, Hongxu Ma, Lan Mu, Stefano Ermon, Tanuja Ganu, Akshay Nambi, Ni Lao, Gengchen Mai
To fill this gap, we propose TorchSpatial, a learning framework and benchmark for location (point) encoding, which is one of the most fundamental data types of spatial representation learning.
1 code implementation • 28 May 2024 • Zhangyu Wang, Krzysztof Janowicz, Gengchen Mai, Ivan Majic
Intuitively, there is a relation between measures of spatial dependence and information theoretical measures of entropy.
1 code implementation • 28 May 2024 • Zhangyu Wang, Gengchen Mai, Krzysztof Janowicz, Ni Lao
A wide range of (multivariate) temporal (1D) and spatial (2D) data analysis tasks, such as grouping vehicle sensor trajectories, can be formulated as clustering with given metric constraints.
no code implementations • 15 Sep 2023 • Zixuan Li, Haiying Lin, Zhangyu Wang, Huazhi Li, Miao Yu, Jie Wang
Unstructured road scenes represented by open-pit mines have irregular boundary lines and uneven road surfaces, which lead to segmentation errors in current ground segmentation methods.
no code implementations • 22 Oct 2022 • Zhangyu Wang, Ningyuan Sun
Recognition of floor plans has been a challenging and popular task.