6 papers
When Bayesian Tensor Completion Meets Multioutput Gaussian Processes: Functional Universality and Rank Learning
Siyuan Li, Shikai Fang, Lei Cheng +4
Functional tensor decomposition can analyze multi-dimensional data with real-valued indices, paving the path for applications in machine learning and signal processing. A limitatio…
An overview of neural architectures for self-supervised audio representation learning from masked spectrograms
Sarthak Yadav, Sergios Theodoridis, Zheng-Hua Tan
In recent years, self-supervised learning has amassed significant interest for training deep neural representations without labeled data. One such self-supervised learning approach…
Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs
Richard Cornelius Suwandi, Feng Yin, Juntao Wang +3
The efficiency of Bayesian optimization (BO) relies heavily on the choice of the Gaussian process (GP) kernel, which plays a central role in balancing exploration and exploitation…
AxLSTMs: learning self-supervised audio representations with xLSTMs
Sarthak Yadav, Sergios Theodoridis, Zheng-Hua Tan
While the transformer has emerged as the eminent neural architecture, several independent lines of research have emerged to address its limitations. Recurrent neural approaches hav…
AudioMAE++: learning better masked audio representations with SwiGLU FFNs
Sarthak Yadav, Sergios Theodoridis, Zheng-Hua Tan
Masked Autoencoders (MAEs) trained on audio spectrogram patches have emerged as a prominent approach for learning self-supervised audio representations. While several recent papers…
FieldFormer: Self-supervised Reconstruction of Physical Fields via Tensor Attention Prior
Panqi Chen, Siyuan Li, Lei Cheng +3
Reconstructing physical field tensors from \textit{in situ} observations, such as radio maps and ocean sound speed fields, is crucial for enabling environment-aware decision making…