Zyphra Launches ZUNA1.1: An Apache 2.0 EEG Model for Variable-Length Inputs
Zyphra has launched ZUNA1.1, an EEG model supporting variable-length inputs from 0.5 to 30 seconds.
Zyphra has introduced the ZUNA1.1 model, capable of processing EEG data with variable-length inputs from 0.5 to 30 seconds. This model addresses the limitations of traditional EEG models by handling real-world recordings and features a 380M masked diffusion autoencoder architecture. It also includes multiple dropout schemes for enhanced performance.