MGU-V: a deep learning approach for lo-fi music generation using variational autoencoders with state-of-the-art performance on combined MIDI datasets
A new framework for generating Lo-Fi music using a hybrid approach combining Long Short-Term Memory (LSTM) networks and Variational Autoencoders (VAEs) capable of producing high-quality music by learning from a curated MIDI dataset
Mathematical formalism for memory compression in selective state space models
Formalizing the trade-off between memory efficiency and information retention to analyse theoretical bounds on the amount of information that can be compressed without sacrificing model performance.
Variational inference for pattern extraction and recognition in genome sequences using state space models for cancer detection
A novel deep-learning framework for cancer-causing mutation detection from genomic data
StructMamba: Structured Harmonic and Temporal Music Analysis via Dual-Axis Mamba and Attention
A dual-axis deep learning architecture that unifies state-space modeling with global two-dimensional attention.
Patents
Transformer-based Model Leveraging Customized Autoregression on Semantic Word Insight
This patent introduces a novel approach to optimizing transformer-based architectures to semantically categorize news articles.
Derivative Works
X Chen - International Journal of Computational Intelligence, 2026 - Springer
ViewQ Huang - Multimedia Systems, 2026 - Springer
ViewY Huang - Journal of the Chinese Institute of Engineers, 2026 - Taylor & Francis
ViewP Xiao - Journal of Computational Methods in Sciences, 2025
ViewH Yan, X Feng, Z Liu - International Journal of Information, 2026 - inderscienceonline
ViewQ Liu - J. COMBIN. MATH. COMBIN. COMPUT, 2025 - combinatorialpress.com
ViewS Somvanshi et. al., ArXiv 2025
ViewJ Tao, T Xu, J Fang, J Xu, Y Liu, Y Liu - International Conference on Intelligent Computing, 2025 - Springer
ViewI'm always looking to collaborate!
If you want to talk about potential collaborations, have questions, or just want to say Hi. You can find me on LinkedIn and I'll be happy to connect with you and explore potential opportunities to work together.
