IEEE

Wasserstein Non-Negative Matrix Factorization for Multi-Layered Graphs and its Application to Mobility Data

Abstract: Multi-layered graphs are popular in mobility studies because transportation data include multiple modalities, such as railways, buses, and taxis. Another example of a multi-layered graph is ...
GitHub

MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views

MAtCha Gaussians reconstruction from 10 input views. We provide a dedicated script for each of these steps, as well as a script train.py that runs the entire pipeline. We explain how to use this ...
GitHub

torch.compile incompatible with CUDA Graph capture due to RNG state access during compilation

When using torch.compile() inside a CUDA Graph capture context, the compilation process fails because it attempts to access CUDA RNG state, which is prohibited during graph capture. This prevents ...
C&EN

Multimodal Cross-Attention Molecular Property Prediction for Text, Sequence, Graph, and Geometry

Article subjects are automatically applied from the ACS Subject Taxonomy and describe the scientific concepts and themes of the article. The disadvantage of unimodal learning is its incapacity to ...
IEEE

Spatial-Temporal Fusion Graph Neural Networks With Mixed Adjacency for Weather Forecasting

Abstract: Rapidly accumulating, large-scale and long-term meteorological data provide unprecedented opportunities for data-driven meteorological models and fine-grained numerical weather prediction.