28 citations · 56 across the 11 of their papers we have counts for
12 papers
SOLO: Pretraining Billion-Parameter Language Models with Shared-Output Local Learning
Bojian Yin, Shurong Wang, Yuqi Pan +1
Large language models are trained with backpropagation, whose global gradient coordinates all layers but forces each to hold its activations and wait for the gradient to pass back…
Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design
Runlin Shi, Bojian Yin, Guoqi Li
Hybrid architectures combining Full Attention (FA) and Linear Attention (LA) are increasingly prominent, yet their allocation remains heuristic. We seek an evidence-grounded basis…
Efficient Sparse Selective-Update RNNs for Long-Range Sequence Modeling
Bojian Yin, Shurong Wang, Haoyu Tan +3
Real-world sequential signals, such as audio or video, contain critical information that is often embedded within long periods of silence or noise. While recurrent neural networks…
Traces Propagation: Memory-Efficient and Scalable Forward-Only Learning in Spiking Neural Networks
Lorenzo Pes, Bojian Yin, Sander Stuijk +1
Spiking Neural Networks (SNNs) provide an efficient framework for processing dynamic spatio-temporal signals and for investigating the learning principles underlying biological neu…
Stochastic Layer-wise Learning: Scalable and Efficient Alternative to Backpropagation
Bojian Yin, Federico Corradi
Backpropagation underpins modern deep learning, yet its reliance on global gradient synchronization limits scalability and incurs high memory costs. In contrast, fully local learni…
Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks
Bojian Yin, Federico Corradi
Recurrent Neural Networks (RNNs) are widely used for sequential processing but face fundamental limitations with continual inference due to state saturation, requiring disruptive h…
Efficient Uncertainty Estimation in Spiking Neural Networks via MC-dropout
Tao Sun, Bojian Yin, Sander Bohte
Spiking neural networks (SNNs) have gained attention as models of sparse and event-driven communication of biological neurons, and as such have shown increasing promise for energy-…
Accurate online training of dynamical spiking neural networks through Forward Propagation Through Time
Bojian Yin, Federico Corradi, Sander M. Bohte
The event-driven and sparse nature of communication between spiking neurons in the brain holds great promise for flexible and energy-efficient AI. Recent advances in learning algor…
Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks
Bojian Yin, Federico Corradi, Sander M. Bohte
Inspired by more detailed modeling of biological neurons, Spiking neural networks (SNNs) have been investigated both as more biologically plausible and potentially more powerful mo…
Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networks
Bojian Yin, Federico Corradi, Sander M. Bohté
The emergence of brain-inspired neuromorphic computing as a paradigm for edge AI is motivating the search for high-performance and efficient spiking neural networks to run on this…
LocalNorm: Robust Image Classification through Dynamically Regularized Normalization
Bojian Yin, Siebren Schaafsma, Henk Corporaal +2
While modern convolutional neural networks achieve outstanding accuracy on many image classification tasks, they are, compared to humans, much more sensitive to image degradation.…
An image representation based convolutional network for DNA classification
Bojian Yin, Marleen Balvert, Davide Zambrano +2
The folding structure of the DNA molecule combined with helper molecules, also referred to as the chromatin, is highly relevant for the functional properties of DNA. The chromatin…