Bridge augments a graph neural network backbone with time-aware retrieval from a memory of region-time windows to improve cold-start and cross-city urban delivery demand forecasting.
arXiv preprint arXiv:2310.06213 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
SynHAT uses a novel two-stage spatio-temporal diffusion framework with Latent Spatio-Temporal U-Net to synthesize realistic human activity traces, outperforming baselines by 52% on spatial and 33% on temporal metrics across four cities.
GIScholarBench shows LLMs exhibit consistent overconfidence across three scholarly tasks in GIS, with different manifestations in factual retrieval, citation expansion, and idea generation.
SLM adds a dedicated spatial modality and training dataset to LLMs, enabling geometric spatial reasoning and outperforming prompt-based symbolic methods on the new SpatialEval benchmark.
A GNN-based foundation model on aggregated US geospatial data produces embeddings achieving SOTA on all 27 interpolation tasks and 25/27 extrapolation/super-resolution tasks across health, socioeconomic and environmental domains, plus improved forecasting when combined with TimesFM.
MobFusion fuses mobility networks into foundation models via three designs and reports improved performance on income, density, and crime prediction tasks using data from three U.S. metropolitan areas.
citing papers explorer
-
Bridge: Retrieval-Augmented Spatiotemporal Modeling for Urban Delivery Demand
Bridge augments a graph neural network backbone with time-aware retrieval from a memory of region-time windows to improve cold-start and cross-city urban delivery demand forecasting.
-
SynHAT: A Two-stage Coarse-to-Fine Diffusion Framework for Synthesizing Human Activity Traces
SynHAT uses a novel two-stage spatio-temporal diffusion framework with Latent Spatio-Temporal U-Net to synthesize realistic human activity traces, outperforming baselines by 52% on spatial and 33% on temporal metrics across four cities.
-
GIScholarBench: Benchmarking LLM Overconfidence in GIS Research
GIScholarBench shows LLMs exhibit consistent overconfidence across three scholarly tasks in GIS, with different manifestations in factual retrieval, citation expansion, and idea generation.
-
From Symbolic to Geometric: Enabling Spatial Reasoning in Large Language Models
SLM adds a dedicated spatial modality and training dataset to LLMs, enabling geometric spatial reasoning and outperforming prompt-based symbolic methods on the new SpatialEval benchmark.
-
General Geospatial Inference with a Population Dynamics Foundation Model
A GNN-based foundation model on aggregated US geospatial data produces embeddings achieving SOTA on all 27 interpolation tasks and 25/27 extrapolation/super-resolution tasks across health, socioeconomic and environmental domains, plus improved forecasting when combined with TimesFM.
-
Enhancing the Socioeconomic Understanding of Foundation Models with Urban Mobility
MobFusion fuses mobility networks into foundation models via three designs and reports improved performance on income, density, and crime prediction tasks using data from three U.S. metropolitan areas.