Ev-DTAD is a novel event-based object detection framework that combines compact temporal event encoding with temporal-relational feature reasoning. Our approach introduces HTA-RGB, a hierarchical ...

Abstract: Hypergraph neural networks (HGNNs) effectively model complex high-order relationships in domains like protein interactions and social networks by connecting multiple vertices through ...

FinD3 implements a Dual 3D State Space model augmented with a dynamic hypergraph for financial stock prediction. This repo provides the code, data provider utilities, model definitions, experiment ...

Abstract: Proactive human-robot collaboration (HRC), as a cognition-centric approach, aims to reason the dynamic process of tasks for proactive robotic decision-making, which can be represented ...

Large Language Models (LLMs) have set new benchmarks in natural language processing, but their tendency for hallucination—generating inaccurate outputs—remains a critical issue for knowledge-intensive ...

Humans collaborate in different contexts such as in creative or scientific projects, in workplaces and in sports. Depending on the project and external circumstances, a newly formed collaboration may ...

Graph theory isn’t enough. The mathematical language for talking about connections, which usually depends on networks — vertices (dots) and edges (lines connecting them) — has been an invaluable way ...

Thanks to Kevin Bacon, everybody nowadays knows about networks. There are not only Bacon-like networks of actors, linked by appearing in the same film, but also social networks, neural networks and ...