3 papers
cs.LG2026
Revisiting Neural Processes via Fourier Transform and Volterra Series
Peiman Mohseni, Nick Duffield, Raymond K. W. Wong
Modeling unknown latent functions from finite, irregularly sampled measurements is a recurring challenge across science and engineering. Neural processes (NPs), a family of probabi…
cs.LG2025
QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration
HamidReza Imani, Jiaxin Peng, Peiman Mohseni +2
The deployment of mixture-of-experts (MoE) large language models (LLMs) presents significant challenges due to their high memory demands. These challenges become even more pronounc…
cs.LG2024
Spectral Convolutional Conditional Neural Processes
Peiman Mohseni, Nick Duffield
Neural Processes (NPs) are meta-learning models that learn to map sets of observations to approximations of the corresponding posterior predictive distributions. By accommodating v…