2 papers
cs.LG2026
ExpertMuon-Compass: Alignment-Guided Step Sizes for Mixture-of-Experts Training
Omatharv Bharat Vaidya, Ashwin Vinod, Pedram Akbarian +3
Mixture-of-experts (MoE) language models send each token to a few experts, so each expert is trained on a different part of the data, and this part changes during training. With a…
physics.flu-dyn2019
Performance and near-wake characterization of a tidal current turbine in elevated levels of free stream turbulence
Ashwin Vinod, Arindam Banerjee
Tidal turbines are deployed in sites which have elevated levels of free stream turbulence (FST). Accounting for elevated FST on their operation become vital from a design standpoin…