4 papers
Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers
Xinzhe Yuan, Xiang Peng, Bin Gu +1
ANN-to-SNN conversion offers a practical, training-free route to spiking large language models. However, current pipelines primarily focus on spike-driven realizations for Transfor…
Vector Quantization in the Brain: Grid-like Codes in World Models
Xiangyuan Peng, Xingsi Dong, Si Wu
We propose Grid-like Code Quantization (GCQ), a brain-inspired method for compressing observation-action sequences into discrete representations using grid-like patterns in attract…
A High-order Backpropagation Algorithm for Neural Stochastic Differential Equation Model
Daili Sheng, Minghui Song, Xiang Peng +1
Neural stochastic differential equation model with a Brownian motion term can capture epistemic uncertainty of deep neural network from the perspective of a dynamical system. The g…
Predictive Learning in Energy-based Models with Attractor Structures
Xingsi Dong, Xiangyuan Peng, Si Wu
Predictive models are highly advanced in understanding the mechanisms of brain function. Recent advances in machine learning further underscore the power of prediction for optimal…