Abstract: The use of natural language interfaces (NLIs) to create charts is becoming increasingly popular due to the intuitiveness of natural language interactions. One key challenge in this approach ...

Abstract: Noninvasive medical neuroimaging has yielded many discoveries about the brain connectivity. Several substantial techniques mapping morphological, structural and functional brain ...

STM-Graph is a Python framework for analyzing spatial-temporal urban data and doing predictions using Graph Neural Networks. It provides a complete end-to-end pipeline from raw event data to trained ...

AEG-Edit improves autoregressive model editing with structured API-evolution and code-context signals. It builds a dual-view heterogeneous graph, aligns the graph representation with the LLM hidden ...