3 papers
cs.LG2026
Preconditioned Inexact Stochastic ADMM for Deep Model
Shenglong Zhou, Ouya Wang, Ziyan Luo +2
Deep learning models are usually trained with stochastic gradient descent-based algorithms, but these optimizers face inherent limitations, such as slow convergence and stringent a…
cs.SD2026
A Lightweight Two-Branch Architecture for Multi-Instrument Transcription via Note-Level Contrastive Clustering
Ruigang Li, Yongxu Zhu
Existing multi-timbre transcription models struggle with generalization beyond pre-trained instruments, rigid source-count constraints, and high computational demands that hinder d…
eess.SP2026
Enabling Green Wireless Communications with Neuromorphic Continual Learning
Yanzhen Liu, Zhijin Qin, Yongxu Zhu +1
The pursuit of carbon-neutral wireless networks is increasingly constrained by the escalating energy demands of deep learning-based signal processing. Here, we introduce SpikACom (…