GitHub

A Step Towards Music Generation Foundation Model

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 ...
Scientific Research Publishing

Machine Learning for Financial Risk Management: Modeling Time-Varying Factor Sensitivities Using Factor Variational Autoencoders ()

Accurate measurement of time-varying systematic risk exposures is essential for robust financial risk management.
C&EN

Mathematical Modeling of Aβ-42 Dimerization Dynamics: Integrating Physics-Based Simulations, Graph-Based Variational Autoencoder-Driven Neural Relational Inference, and Chaos ...

Computational Biology and Molecular Simulations Laboratory, Department of Biophysics, School of Medicine, Bahçeşehir University, Istanbul 34349, Turkey Lab for Innovative Drugs (Lab4IND), ...
IEEE

Blind Polarisation Demultiplexing and Carrier Recovery Using FIR-based Variational AutoEncoder Equaliser for Probabilistic Constellation Shaping in Optical Fibre Communications

Abstract: We investigate through simulations the potential of Finite Impulse Response (FIR)-based Variational AutoEncoder-inspired (VAE-FIR) equaliser for polarisation demultiplexing, Carrier Phase ...
IEEE

Toward Adaptive and Interpretable Process Monitoring: Incremental Variational Graph Attention Autoencoder With Probabilistic Inference

Abstract: Complex industrial processes exhibit typical nonstationarity due to frequently fluctuating material flows and complex control loops. This poses three challenges for trustworthy process ...