Related papers: Parallelized Hierarchical Connectome: A Spatiotemp…
Brain-computer interfaces (BCIs) are an advanced fusion of neuroscience and artificial intelligence, requiring stable and long-term decoding of neural signals. Spiking Neural Networks (SNNs), with their neuronal dynamics and spike-based…
Sequence modeling is crucial for AI to understand temporal data and detect complex time-dependent patterns. While recurrent neural networks (RNNs), convolutional neural networks (CNNs), and Transformers have advanced in capturing long-range…
Spiking neural networks have garnered increasing attention due to their energy efficiency, multiplication-free computation, and sparse event-based processing. In parallel, state space models have emerged as scalable alternatives to…
We introduce a particle-based framework inspired by smoothed particle hydrodynamics (SPH) to simulate the dynamics of a continuous field of coupled phase oscillators. This methodology discretizes the spatial domain into particles and…
In this paper, we propose a novel semantic-aided image communication framework for supporting the compatibility with practical separation-based coding architectures. Particularly, the deep learning (DL)-based joint source-channel coding…
Spiking recurrent neural networks (RNNs) are a promising tool for solving a wide variety of complex cognitive and motor tasks, due to their rich temporal dynamics and sparse processing. However training spiking RNNs on dedicated…
Selective state space models (SSMs) have rapidly become a compelling backbone for large language models, especially for long-context workloads. Yet in deployment, their inference performance is often bounded by the memory capacity,…
The Single Program Multiple Data (SPMD) paradigm provides a unified abstraction to annotate various parallel dimensions in distributed deep learning (DL) training. With SPMD, users can write training programs from the viewpoint of a single…
Brain connectomics is still largely dominated by pairwise-based models, such as graphs, which cannot represent circulatory or higher-order functional interactions. In this paper, we propose a multimodal framework based on Topological Signal…
With serial and parallel processors introduced into Spiking Neural Networks (SNNs) execution, more and more researchers are dedicated to improving the performance of the computing paradigms by taking full advantage of the strengths of the…
The integration of image and event streams offers a promising approach for achieving robust visual object tracking in complex environments. However, current fusion methods achieve high performance at the cost of significant computational…
This paper presents a massively parallel and scalable neuromorphic cortex simulator designed for simulating large and structurally connected spiking neural networks, such as complex models of various areas of the cortex. The main novelty of…
Recurrent Neural Networks (RNNs) laid the foundation for sequence modeling, but their intrinsic sequential nature restricts parallel computation, creating a fundamental barrier to scaling. This has led to the dominance of parallelizable…
The multi-level hp-refinement scheme is a powerful extension of the finite element method that allows local mesh adaptation without the trouble of constraining hanging nodes. This is achieved through hierarchical high-order overlay meshes,…
Inspired by the brain's spike-based computation, spiking neural networks (SNNs) inherently possess temporal activation sparsity. However, when it comes to the sparse training of SNNs in the structural connection domain, existing methods…
Spiking Neural Networks (SNNs) are efficient computation models to perform spatio-temporal pattern recognition on {resource}- and {power}-constrained platforms. SNNs executed on neuromorphic hardware can further reduce energy consumption of…
Neuromorphic computing and spiking neural networks (SNN) mimic the behavior of biological systems and have drawn interest for their potential to perform cognitive tasks with high energy efficiency. However, some factors such as temporal…
Time series modeling is a well-established problem, which often requires that methods (1) expressively represent complicated dependencies, (2) forecast long horizons, and (3) efficiently train over long sequences. State-space models (SSMs)…
Stencil computation is one of the fundamental computing patterns in many application domains such as scientific computing and image processing. While there are promising studies that accelerate stencils on FPGAs, there lacks an automated…
Spiking neural networks (SNN) are artificial computational models that have been inspired by the brain's ability to naturally encode and process information in the time domain. The added temporal dimension is believed to render them more…