Abstract: Masked Autoencoder (MAE) has shown remarkable potential in self-supervised representation learning for 3D point clouds. However, these methods primarily rely on point-level or low-level ...

Abstract: Hyperspectral unmixing (HU) aims to decompose mixed pixels into their constituent spectral signatures and estimate their corresponding fractional abundances. Recently, the nonlinear spectral ...

PyTorch reimplementation of "Deep Hierarchical Planning" RL framework. Features a multi-model architecture with manager-worker policies, world model, and goal autoencoder. Built with Python/PyTorch ...

We introduce ACE-Step, a novel open-source foundation model for music generation that overcomes key limitations of existing approaches and achieves state-of-the-art performance through a holistic ...