While supervised methods are effective, they require extensive labeled data for training. Recently, self-supervised foundation models have been introduced to these tasks showing comparable results to supervised methods.

V2A model based on rectified flow matching.

Machine learning for node classification on graphs is a prominent area driven by applications such as recommendation systems.

Temporal Domain Generalization (TDG) addresses the challenge of training predictive models under temporally varying data distributions. Traditional TDG approaches typically focus on domain data collected at fixed, discrete time intervals, which limits their capability to capture the inherent dynamics within continuous-evolving and irregularly-observed temporal domains.

We show that it provides significant benefits to RL agents on a suite of gridworld, CARL and MetaWorld tasks.

ASNPE brings an active learning scheme into the inference loop to estimate the utility of simulation parameter candidates to the underlying probabilistic model.

Dancing to the musical beats or creating a variety of rhythmically synchronized music for a given motion is a fundamental aspect of human creativity.