4 papers · 1 filter
Collapse or Preserve: Data-Dependent Temporal Aggregation for Spiking Neural Network Acceleration
Jiahao Qin
Spike sparsity is widely believed to enable efficient spiking neural network (SNN) inference on GPU hardware. We demonstrate this is an illusion: five distinct sparse computation s…
mlx-snn: Spiking Neural Networks on Apple Silicon via MLX
Jiahao Qin
We introduce mlx-snn, the first spiking neural network (SNN) library built natively on Apple's MLX framework. As SNN research grows rapidly, all major libraries -- snnTorch, Norse,…
DUAL: Dynamic Uncertainty-Aware Learning
Jiahao Qin, Bei Peng, Feng Liu +2
Deep learning models frequently encounter feature uncertainty in diverse learning scenarios, significantly impacting their performance and reliability. This challenge is particular…
Hierarchical Adaptive Expert for Multimodal Sentiment Analysis
Jiahao Qin, Feng Liu, Lu Zong
Multimodal sentiment analysis has emerged as a critical tool for understanding human emotions across diverse communication channels. While existing methods have made significant st…