Search Results for author:
Found 10 papers, 4 papers with code
ELITE: Embedding-Less retrieval with Iterative Text Exploration
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.
LocDiffusion: Identifying Locations on Earth by Diffusing in the Hilbert Space
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.
The S2 Hierarchical Discrete Global Grid as a Nexus for Data Representation, Integration, and Querying Across Geospatial Knowledge Graphs
Geospatial Knowledge Graphs (GeoKGs) have become integral to the growing field of Geospatial Artificial Intelligence.
The KnowWhereGraph Ontology
KnowWhereGraph is one of the largest fully publicly available geospatial knowledge graphs.
A Geometry-Aware Algorithm to Learn Hierarchical Embeddings in Hyperbolic Space
Hyperbolic embeddings are a class of representation learning methods that offer competitive performances when data can be abstracted as a tree-like graph.
TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning
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.
Probing the Information Theoretical Roots of Spatial Dependence Measures
Intuitively, there is a relation between measures of spatial dependence and information theoretical measures of entropy.
MC-GTA: Metric-Constrained Model-Based Clustering using Goodness-of-fit Tests with Autocorrelations
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.
A Ground Segmentation Method Based on Point Cloud Map for Unstructured Roads
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.
Offset-Guided Attention Network for Room-Level Aware Floor Plan Segmentation
Recognition of floor plans has been a challenging and popular task.
