papers

Publications (80)

cs.CV2026

SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike Streams

Zhuoheng Gao, Yihao Li, Jiyao Zhang +7

Conventional frame-based cameras often struggle with stereo depth estimation in rapidly changing scenes. In contrast, bio-inspired spike cameras emit asynchronous events at microse…

cs.CV2025

Differential Coding for Training-Free ANN-to-SNN Conversion

Zihan Huang, Wei Fang, Tong Bu +6

Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption. Converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achiev…

cs.NE2025

TDFormer: A Top-Down Attention-Controlled Spiking Transformer

Zizheng Zhu, Yingchao Yu, Zeqi Zheng +2

Traditional spiking neural networks (SNNs) can be viewed as a combination of multiple subnetworks with each running for one time step, where the parameters are shared, and the memb…

cs.NE2022

Deep Residual Learning in Spiking Neural Networks

Wei Fang, Zhaofei Yu, Yanqi Chen +3

Deep Spiking Neural Networks (SNNs) present optimization difficulties for gradient-based approaches due to discrete binary activation and complex spatial-temporal dynamics. Conside…

cs.CV2024

Towards Low-latency Event-based Visual Recognition with Hybrid Step-wise Distillation Spiking Neural Networks

Xian Zhong, Shengwang Hu, Wenxuan Liu +4

Spiking neural networks (SNNs) have garnered significant attention for their low power consumption and high biological interpretability. Their rich spatio-temporal information proc…

cs.LG2023

One Forward is Enough for Neural Network Training via Likelihood Ratio Method

Jinyang Jiang, Zeliang Zhang, Chenliang Xu +2

While backpropagation (BP) is the mainstream approach for gradient computation in neural network training, its heavy reliance on the chain rule of differentiation constrains the de…

cs.LG2026

AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning

Shengyang Li, Yiting Dong, Liuyang Song +5

Federated learning enables collaborative model training across distributed edge devices while strictly preserving data privacy. To facilitate practical deployment on resource-const…

q-bio.NC2020

Towards the Next Generation of Retinal Neuroprosthesis: Visual Computation with Spikes

Zhaofei Yu, Jian K. Liu, Shanshan Jia +4

Neuroprosthesis, as one type of precision medicine device, is aiming for manipulating neuronal signals of the brain in a closed-loop fashion, together with receiving stimulus from…

cs.NE2026

GemS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer

Zecheng Hao, Shenghao Xie, Kang Chen +3

Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs). However, they encounter significant deficiencies in training and inference m…

cs.NE2026

Rethinking SNN Online Training and Deployment: Gradient-Coherent Learning via Hybrid-Driven LIF Model

Zecheng Hao, Yifan Huang, Zijie Xu +4

Spiking Neural Networks (SNNs) are considered to have enormous potential in the future development of Artificial Intelligence due to their brain-inspired and energy-efficient prope…

cs.CV2025

HAD: Hierarchical Asymmetric Distillation to Bridge Spatio-Temporal Gaps in Event-Based Object Tracking

Yao Deng, Xian Zhong, Wenxuan Liu +3

RGB cameras excel at capturing rich texture details with high spatial resolution, whereas event cameras offer exceptional temporal resolution and a high dynamic range (HDR). Levera…

cs.CV2025

Rethinking High-speed Image Reconstruction Framework with Spike Camera

Kang Chen, Yajing Zheng, Tiejun Huang +1

Spike cameras, as innovative neuromorphic devices, generate continuous spike streams to capture high-speed scenes with lower bandwidth and higher dynamic range than traditional RGB…

cs.NE2025

Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation

Yiting Dong, Zhaofei Yu, Jianhao Ding +2

Spiking Neural Networks (SNNs) are considered naturally suited for temporal processing, with membrane potential propagation widely regarded as the core temporal modeling mechanism.…

cs.CV2024

SpikeMM: Flexi-Magnification of High-Speed Micro-Motions

Baoyue Zhang, Yajing Zheng, Shiyan Chen +4

The amplification of high-speed micro-motions holds significant promise, with applications spanning fault detection in fast-paced industrial environments to refining precision in m…

cs.NE2024

SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks

Xinyu Shi, Zecheng Hao, Zhaofei Yu

The remarkable success of Vision Transformers in Artificial Neural Networks (ANNs) has led to a growing interest in incorporating the self-attention mechanism and transformer-based…

cs.CV2024

SpikeCV: Open a Continuous Computer Vision Era

Yajing Zheng, Jiyuan Zhang, Rui Zhao +5

SpikeCV is a new open-source computer vision platform for the spike camera, which is a neuromorphic visual sensor that has developed rapidly in recent years. In the spike camera, e…

cs.NE2026

CaRe-BN: Precise Moving Statistics for Stabilizing Spiking Neural Networks in Reinforcement Learning

Zijie Xu, Xinyu Shi, Yiting Dong +2

Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision-making on neuromorphic hardware by mimicking the event-driven dynamics of biological neurons. However…

cs.CV2022

Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation

Ziluo Ding, Rui Zhao, Jiyuan Zhang +4

Event camera has offered promising alternative for visual perception, especially in high speed and high dynamic range scenes. Recently, many deep learning methods have shown great…

cs.NE2025

SpiLiFormer: Enhancing Spiking Transformers with Lateral Inhibition

Zeqi Zheng, Yanchen Huang, Yingchao Yu +4

Spiking Neural Networks (SNNs) based on Transformers have garnered significant attention due to their superior performance and high energy efficiency. However, the spiking attentio…

cs.LG2023

A Unified Framework for Soft Threshold Pruning

Yanqi Chen, Zhengyu Ma, Wei Fang +3

Soft threshold pruning is among the cutting-edge pruning methods with state-of-the-art performance. However, previous methods either perform aimless searching on the threshold sche…

cs.NE2026

Error Amplification Limits ANN-to-SNN Conversion in Continuous Control

Zijie Xu, Zihan Huang, Yiting Dong +3

Spiking Neural Networks (SNNs) can achieve competitive performance by converting already existing well-trained Artificial Neural Networks (ANNs), avoiding further costly training.…

q-bio.NC2020

Revealing Fine Structures of the Retinal Receptive Field by Deep Learning Networks

Qi Yan, Yajing Zheng, Shanshan Jia +6

Deep convolutional neural networks (CNNs) have demonstrated impressive performance on many visual tasks. Recently, they became useful models for the visual system in neuroscience.…

cs.CV2023

Unveiling the Potential of Spike Streams for Foreground Occlusion Removal from Densely Continuous Views

Jiyuan Zhang, Shiyan Chen, Yajing Zheng +2

The extraction of a clean background image by removing foreground occlusion holds immense practical significance, but it also presents several challenges. Presently, the majority o…

cs.NE2024

Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks

Lihao Wang, Zhaofei Yu

Spiking Neural Networks (SNNs) emulate the integrated-fire-leak mechanism found in biological neurons, offering a compelling combination of biological realism and energy efficiency…

q-bio.NC2024

Deep Learning for Visual Neuroprosthesis

Peter Beech, Shanshan Jia, Zhaofei Yu +1

The visual pathway involves complex networks of cells and regions which contribute to the encoding and processing of visual information. While some aspects of visual perception are…

q-bio.NC2020

Neural System Identification with Spike-triggered Non-negative Matrix Factorization

Shanshan Jia, Zhaofei Yu, Arno Onken +3

Neuronal circuits formed in the brain are complex with intricate connection patterns. Such complexity is also observed in the retina as a relatively simple neuronal circuit. A reti…

cs.CV2024

Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios

Shiyan Chen, Jiyuan Zhang, Zhaofei Yu +1

Self-supervised denoising has attracted widespread attention due to its ability to train without clean images. However, noise in real-world scenarios is often spatially correlated,…

cs.NE2023

Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikes

Zecheng Hao, Jianhao Ding, Tong Bu +2

Spiking Neural Networks (SNNs) have attracted great attention due to their distinctive characteristics of low power consumption and temporal information processing. ANN-SNN convers…

q-bio.NC2025

Implementing feature binding through dendritic networks of a single neuron

Yuanhong Tang, Shanshan Jia, Tiejun Huang +2

A single neuron receives an extensive array of synaptic inputs through its dendrites, raising the fundamental question of how these inputs undergo integration and summation, culmin…

eess.IV2023

INeAT: Iterative Neural Adaptive Tomography

Bo Xiong, Changqing Su, Zihan Lin +2

Computed Tomography (CT) with its remarkable capability for three-dimensional imaging from multiple projections, enjoys a broad range of applications in clinical diagnosis, scienti…

cs.NE2021

Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks

Wei Fang, Zhaofei Yu, Yanqi Chen +3

Spiking Neural Networks (SNNs) have attracted enormous research interest due to temporal information processing capability, low power consumption, and high biological plausibility.…

cs.CV2025

SOTA: Spike-Navigated Optimal TrAnsport Saliency Region Detection in Composite-bias Videos

Wenxuan Liu, Yao Deng, Kang Chen +3

Existing saliency detection methods struggle in real-world scenarios due to motion blur and occlusions. In contrast, spike cameras, with their high temporal resolution, significant…

cs.CV2026

SPKLIP: Aligning Spike Video Streams with Natural Language

Yongchang Gao, Meiling Jin, Zhaofei Yu +2

Spike cameras offer unique sensing capabilities but their sparse, asynchronous output challenges semantic understanding, especially for Spike Video-Language Alignment (Spike-VLA) w…

cs.NE2025

Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculation

Zecheng Hao, Qichao Ma, Kang Chen +3

Spiking Neural Network (SNN), as a brain-inspired and energy-efficient network, is currently facing the pivotal challenge of exploring a suitable and efficient learning framework.…

q-bio.NC2018

Winner-Take-All as Basic Probabilistic Inference Unit of Neuronal Circuits

Zhaofei Yu, Yonghong Tian, Tiejun Huang +1

Experimental observations of neuroscience suggest that the brain is working a probabilistic way when computing information with uncertainty. This processing could be modeled as Bay…

cs.CV2025

SpikeDerain: Unveiling Clear Videos from Rainy Sequences Using Color Spike Streams

Hanwen Liang, Xian Zhong, Wenxuan Liu +4

Restoring clear frames from rainy videos presents a significant challenge due to the rapid motion of rain streaks. Traditional frame-based visual sensors, which capture scene conte…

cs.CV2026

Brain-Inspired Multimodal Spiking Neural Network for Image-Text Retrieval

Xintao Zong, Xian Zhong, Wenxuan Liu +3

Spiking neural networks (SNNs) have recently shown strong potential in unimodal visual and textual tasks, yet building a directly trained, low-energy, and high-performance SNN for…

cs.NE2023

Deep Pulse-Coupled Neural Networks

Zexiang Yi, Jing Lian, Yunliang Qi +4

Spiking Neural Networks (SNNs) capture the information processing mechanism of the brain by taking advantage of spiking neurons, such as the Leaky Integrate-and-Fire (LIF) model ne…

cs.CV2023

Spike Stream Denoising via Spike Camera Simulation

Liwen hu, Lei Ma, Zhaofei Yu +2

As a neuromorphic sensor with high temporal resolution, the spike camera shows enormous potential in high-speed visual tasks. However, the high-speed sampling of light propagation…

cs.NE2023

Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks

Tong Bu, Wei Fang, Jianhao Ding +3

Spiking Neural Networks (SNNs) have gained great attraction due to their distinctive properties of low power consumption and fast inference on neuromorphic hardware. As the most ef…

cs.NE2018

CaMKII activation supports reward-based neural network optimization through Hamiltonian sampling

Zhaofei Yu, David Kappel, Robert Legenstein +3

Synaptic plasticity is implemented and controlled through over thousand different types of molecules in the postsynaptic density and presynaptic boutons that assume a staggering ar…

cs.NE2026

Latency Coding for Efficient and Low-Latency Deep Spiking Neural Networks

Yi Lu, Jianhao Ding, Zhaofei Yu

The paper introduces latency coding, an extension of time‑to‑first‑spike coding, and a training framework using backpropagation through time to build deep spiking neural networks t…

#spiking neural networks#latency coding#energy efficiency#backpropagation through time
cs.NE2022

Optimized Potential Initialization for Low-latency Spiking Neural Networks

Tong Bu, Jianhao Ding, Zhaofei Yu +1

Spiking Neural Networks (SNNs) have been attached great importance due to the distinctive properties of low power consumption, biological plausibility, and adversarial robustness.…

q-bio.NC2020

Probabilistic Inference of Binary Markov Random Fields in Spiking Neural Networks through Mean-field Approximation

Yajing Zheng, Shanshan Jia, Zhaofei Yu +3

Recent studies have suggested that the cognitive process of the human brain is realized as probabilistic inference and can be further modeled by probabilistic graphical models like…

cs.LG2023

A Novel Noise Injection-based Training Scheme for Better Model Robustness

Zeliang Zhang, Jinyang Jiang, Minjie Chen +3

Noise injection-based method has been shown to be able to improve the robustness of artificial neural networks in previous work. In this work, we propose a novel noise injection-ba…

cs.CV2025

Driving in Spikes: An Entropy-Guided Object Detector for Spike Cameras

Ziyan Liu, Qi Su, Lulu Tang +2

Object detection in autonomous driving suffers from motion blur and saturation under fast motion and extreme lighting. Spike cameras, offer microsecond latency and ultra high dynam…

cs.RO2026

SpikeGrasp: A Benchmark for 6-DoF Grasp Pose Detection from Stereo Spike Streams

Zhuoheng Gao, Jiyao Zhang, Zhiyong Xie +5

Most robotic grasping systems rely on converting sensor data into explicit 3D point clouds, which is a computational step not found in biological intelligence. This paper explores…

cs.CV2026

Spike Imaging Velocimetry: Dense Motion Estimation of Fluids Using Spike Cameras

Yunzhong Zhang, Bo Xiong, You Zhou +5

Particle Image Velocimetry (PIV) is a widely adopted non-invasive imaging technique that tracks the motion of tracer particles across image sequences to capture the velocity distri…

cs.CV2026

High-Speed Full-Color HDR Imaging via Unwrapping Modulo-Encoded Spike Streams

Chu Zhou, Siqi Yang, Kailong Zhang +4

Conventional RGB-based high dynamic range (HDR) imaging faces a fundamental trade-off between motion artifacts in multi-exposure captures and irreversible information loss in singl…

cs.NE2026

Training Deep Normalization-Free Spiking Neural Networks with Lateral Inhibition

Peiyu Liu, Jianhao Ding, Zhaofei Yu

Spiking Neural Networks (SNNs) have garnered significant attention as a central paradigm in neuromorphic computing, owing to their energy efficiency and biological plausibility. Ho…

cs.NE2015

Sampling-based Causal Inference in Cue Combination and its Neural Implementation

Zhaofei Yu, Feng Chen, Jianwu Dong +1

Causal inference in cue combination is to decide whether the cues have a single cause or multiple causes. Although the Bayesian causal inference model explains the problem of causa…

cs.CV2025

USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting

Kang Chen, Jiyuan Zhang, Zecheng Hao +3

Spike cameras, as an innovative neuromorphic camera that captures scenes with the 0-1 bit stream at 40 kHz, are increasingly employed for the 3D reconstruction task via Neural Radi…

cs.CV2025

Inter-event Interval Microscopy for Event Cameras

Changqing Su, Yanqin Chen, Zihan Lin +5

Event cameras, an innovative bio-inspired sensor, differ from traditional cameras by sensing changes in intensity rather than directly perceiving intensity and recording these vari…

cs.CL2026

Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture

Qichao Ma, Rui-Jie Zhu, Peiye Liu +8

Large Language Models (LLMs) utilize extensive knowledge databases and show powerful text generation ability. However, their reliance on high-quality copyrighted datasets raises co…

q-bio.NC2025

A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing

Yu Chen, Jing Lian, Zhaofei Yu +3

Event cameras are bio-inspired vision sensor that encode visual information with high dynamic range, high temporal resolution, and low latency.Current state-of-the-art event stream…

cs.CV2025

Towards High-performance Spiking Transformers from ANN to SNN Conversion

Zihan Huang, Xinyu Shi, Zecheng Hao +4

Spiking neural networks (SNNs) show great potential due to their energy efficiency, fast processing capabilities, and robustness. There are two main approaches to constructing SNNs…

cs.NE2024

Converting High-Performance and Low-Latency SNNs through Explicit Modelling of Residual Error in ANNs

Zhipeng Huang, Jianhao Ding, Zhiyu Pan +4

Spiking neural networks (SNNs) have garnered interest due to their energy efficiency and superior effectiveness on neuromorphic chips compared with traditional artificial neural ne…

cs.NE2021

Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks

Jianhao Ding, Zhaofei Yu, Yonghong Tian +1

Spiking Neural Networks (SNNs), as bio-inspired energy-efficient neural networks, have attracted great attentions from researchers and industry. The most efficient way to train dee…

cs.LG2026

: Online RL Fine-tuning for Flow-based Vision-Language-Action Models

Kang Chen, Zhihao Liu, Tonghe Zhang +11

Vision-Language-Action (VLA) models enable robots to understand and perform complex tasks from multimodal input. Although recent work explores using reinforcement learning (RL) to…

q-bio.NC2020

Reconstruction of Natural Visual Scenes from Neural Spikes with Deep Neural Networks

Yichen Zhang, Shanshan Jia, Yajing Zheng +5

Neural coding is one of the central questions in systems neuroscience for understanding how the brain processes stimulus from the environment, moreover, it is also a cornerstone fo…

cs.NE2025

Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications

Tong Bu, Maohua Li, Zhaofei Yu

Spiking Neural Networks (SNNs) have emerged as a promising substitute for Artificial Neural Networks (ANNs) due to their advantages of fast inference and low power consumption. How…

cs.CV2024

SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams

Kang Chen, Shiyan Chen, Jiyuan Zhang +4

Reconstructing a sequence of sharp images from the blurry input is crucial for enhancing our insights into the captured scene and poses a significant challenge due to the limited t…

stat.ML2017

Revealing structure components of the retina by deep learning networks

Qi Yan, Zhaofei Yu, Feng Chen +1

Deep convolutional neural networks (CNNs) have demonstrated impressive performance on visual object classification tasks. In addition, it is a useful model for predication of neuro…

cs.NE2026

SpikingMOT: A Spike-Driven Multi-Object Tracker

Yiding Sun, Xiangyang Yang, Dongxu Zhang +7

Multi-object tracking (MOT) plays a fundamental role in visual perception, where accurate trajectory prediction is essential for reliable target association under complex motion pa…

cs.NE2026

PredNext: Explicit Cross-View Temporal Prediction for Unsupervised Learning in Spiking Neural Networks

Yiting Dong, Jianhao Ding, Zijie Xu +3

Spiking Neural Networks (SNNs), with their temporal processing capabilities and biologically plausible dynamics, offer a natural platform for unsupervised representation learning.…

q-bio.NC2023

Spike timing reshapes robustness against attacks in spiking neural networks

Jianhao Ding, Zhaofei Yu, Tiejun Huang +1

The success of deep learning in the past decade is partially shrouded in the shadow of adversarial attacks. In contrast, the brain is far more robust at complex cognitive tasks. Ut…

cs.NE2021

Pruning of Deep Spiking Neural Networks through Gradient Rewiring

Yanqi Chen, Zhaofei Yu, Wei Fang +2

Spiking Neural Networks (SNNs) have been attached great importance due to their biological plausibility and high energy-efficiency on neuromorphic chips. As these chips are usually…

cs.NE2025

STF: Shallow-Level Temporal Feedback to Enhance Spiking Transformers

Zeqi Zheng, Zizheng Zhu, Yingchao Yu +5

Transformer-based Spiking Neural Networks (SNNs) suffer from a great performance gap compared to floating-point \mbox{Artificial} Neural Networks (ANNs) due to the binary nature of…

cs.CV2024

SpikeGS: 3D Gaussian Splatting from Spike Streams with High-Speed Camera Motion

Jiyuan Zhang, Kang Chen, Shiyan Chen +3

Novel View Synthesis plays a crucial role by generating new 2D renderings from multi-view images of 3D scenes. However, capturing high-speed scenes with conventional cameras often…

cs.NE2026

Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control

Zijie Xu, Tong Bu, Zecheng Hao +2

Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision making on neuromorphic hardware, making them attractive for Reinforcement Learning (RL) in resource-c…

cs.CV2022

1000x Faster Camera and Machine Vision with Ordinary Devices

Tiejun Huang, Yajing Zheng, Zhaofei Yu +13

In digital cameras, we find a major limitation: the image and video form inherited from a film camera obstructs it from capturing the rapidly changing photonic world. Here, we pres…

cs.NE2024

Enhancing Adversarial Robustness in SNNs with Sparse Gradients

Yujia Liu, Tong Bu, Jianhao Ding +3

Spiking Neural Networks (SNNs) have attracted great attention for their energy-efficient operations and biologically inspired structures, offering potential advantages over Artific…

cs.NE2023

Reducing ANN-SNN Conversion Error through Residual Membrane Potential

Zecheng Hao, Tong Bu, Jianhao Ding +2

Spiking Neural Networks (SNNs) have received extensive academic attention due to the unique properties of low power consumption and high-speed computing on neuromorphic chips. Amon…

cs.NE2026

General Self-Prediction Enhancement for Spiking Neurons

Zihan Huang, Zijie Xu, Yihan Huang +7

Spiking Neural Networks (SNNs) are highly energy-efficient due to event-driven, sparse computation, but their training is challenged by spike non-differentiability and trade-offs a…

cs.NE2024

LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model

Zecheng Hao, Xinyu Shi, Yujia Liu +2

Compared to traditional Artificial Neural Network (ANN), Spiking Neural Network (SNN) has garnered widespread academic interest for its intrinsic ability to transmit information in…

cs.NE2023

SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence

Wei Fang, Yanqi Chen, Jianhao Ding +7

Spiking neural networks (SNNs) aim to realize brain-inspired intelligence on neuromorphic chips with high energy efficiency by introducing neural dynamics and spike properties. As…

cs.NE2024

Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies

Wei Fang, Zhaofei Yu, Zhaokun Zhou +5

Vanilla spiking neurons in Spiking Neural Networks (SNNs) use charge-fire-reset neuronal dynamics, which can only be simulated serially and can hardly learn long-time dependencies.…

cs.NE2024

Robust Stable Spiking Neural Networks

Jianhao Ding, Zhiyu Pan, Yujia Liu +2

Spiking neural networks (SNNs) are gaining popularity in deep learning due to their low energy budget on neuromorphic hardware. However, they still face challenges in lacking suffi…

cs.CV2023

Unsupervised Optical Flow Estimation with Dynamic Timing Representation for Spike Camera

Lujie Xia, Ziluo Ding, Rui Zhao +5

Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timin…

cs.LG2026

Uncertainty-Aware Token Importance Estimation in Spiking Transformers

Wenxuan Liu, Zecheng Hao, Tong Bu +2

Spiking transformers have shown strong potential for neuromorphic vision, yet their token processing across multiple spiking steps still introduces substantial redundancy and infer…