The graphics processing unit (GPU) did not begin as a pillar of supercomputing or the engine behind artificial‑intelligence ...

SIGGRAPH has long been a launchpad for technologies that quickly move from the lab to real-world deployment. Each year, ...

To overcome these limitations, we propose a Spatial-Temporal Interactive Dynamic Graph Convolutional Network (STIDGCN) for traffic forecasting. Specifically, we propose an interactive learning ...

Hierarchical reinforcement learning (HRL) incorporates temporal abstraction into reinforcement learning (RL) by explicitly taking advantage of hierarchical structures. Modern HRL typically designs a ...

Creating a lifelike digital replica of a physical space no longer requires specialized equipment or labor-intensive manual mapping. A new system, DRAWER, developed by researchers at Cornell University ...