Gang Pan
YOU?
Author Swipe
View article: Unveiling interactions of spatial-temporal information in tactile motion perception
Unveiling interactions of spatial-temporal information in tactile motion perception Open
Tactile perception is inherently dynamic, relying on active manual exploration to extract information about motion and surface properties. Spatiotemporal inputs facilitate tactile motion perception by conveying information both direction a…
View article: Monolithic multimodal neural probes for sustained stimulation and long-term neural recording
Monolithic multimodal neural probes for sustained stimulation and long-term neural recording Open
Long-term implantable neural probes with dual-mode optical stimulation and simultaneous electrical recording are crucial for modulating neural loop activity in vivo. Traditional probes using “add-on” strategies often suffer from mechanical…
View article: SPICED: A Synaptic Homeostasis-Inspired Framework for Unsupervised Continual EEG Decoding
SPICED: A Synaptic Homeostasis-Inspired Framework for Unsupervised Continual EEG Decoding Open
Human brain achieves dynamic stability-plasticity balance through synaptic homeostasis. Inspired by this biological principle, we propose SPICED: a neuromorphic framework that integrates the synaptic homeostasis mechanism for unsupervised …
View article: DarwinWafer: A Wafer-Scale Neuromorphic Chip
DarwinWafer: A Wafer-Scale Neuromorphic Chip Open
Neuromorphic computing promises brain-like efficiency, yet today's multi-chip systems scale over PCBs and incur orders-of-magnitude penalties in bandwidth, latency, and energy, undermining biological algorithms and system efficiency. We pr…
View article: Task-structured Modularity Emerges in Artificial Networks and Aligns with Brain Architecture
Task-structured Modularity Emerges in Artificial Networks and Aligns with Brain Architecture Open
Understanding how neural systems develop modular organization is fundamental to both neuroscience and artificial intelligence. Although modular architectures can improve adaptability and cognitive performance, the processes leading to thei…
View article: Edge Intelligence with Spiking Neural Networks
Edge Intelligence with Spiking Neural Networks Open
The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditional deep learning models require significant computational …
View article: Neural-Driven Image Editing
Neural-Driven Image Editing Open
Traditional image editing typically relies on manual prompting, making it labor-intensive and inaccessible to individuals with limited motor control or language abilities. Leveraging recent advances in brain-computer interfaces (BCIs) and …
View article: A Unified Flexible Large Polysomnography Model for Sleep Staging and Mental Disorder Diagnosis
A Unified Flexible Large Polysomnography Model for Sleep Staging and Mental Disorder Diagnosis Open
Sleep disorders affect billions worldwide, yet clinical polysomnography (PSG) analysis remains hindered by labor-intensive manual scoring and limited generalizability of automated sleep staging tools across heterogeneous protocols. We pres…
View article: Spiking Neural Networks with Temporal Attention-Guided Adaptive Fusion for imbalanced Multi-modal Learning
Spiking Neural Networks with Temporal Attention-Guided Adaptive Fusion for imbalanced Multi-modal Learning Open
Multimodal spiking neural networks (SNNs) hold significant potential for energy-efficient sensory processing but face critical challenges in modality imbalance and temporal misalignment. Current approaches suffer from uncoordinated converg…
View article: Bridging Quantized Artificial Neural Networks and Neuromorphic Hardware
Bridging Quantized Artificial Neural Networks and Neuromorphic Hardware Open
Neuromorphic hardware aims to leverage distributed computing and event-driven circuit design to achieve an energy-efficient AI system. The name "neuromorphic" is derived from its spiking and local computing nature, which mimics the fundame…
View article: Variation-resilient spike-timing-dependent plasticity in memristors using bursting neuron circuit
Variation-resilient spike-timing-dependent plasticity in memristors using bursting neuron circuit Open
Spike-timing-dependent plasticity (STDP) is a classic synaptic function that facilitates learning and memory in a biological brain. Hardware implementation of neural circuits supporting dynamical STDP functions offers notable advantages in…
View article: Human-like Cognitive Generalization for Large Models via Brain-in-the-loop Supervision
Human-like Cognitive Generalization for Large Models via Brain-in-the-loop Supervision Open
Recent advancements in deep neural networks (DNNs), particularly large-scale language models, have demonstrated remarkable capabilities in image and natural language understanding. Although scaling up model parameters with increasing volum…
View article: Hybrid Spiking Vision Transformer for Object Detection with Event Cameras
Hybrid Spiking Vision Transformer for Object Detection with Event Cameras Open
Event-based object detection has gained increasing attention due to its advantages such as high temporal resolution, wide dynamic range, and asynchronous address-event representation. Leveraging these advantages, Spiking Neural Networks (S…
View article: EvoMoE: Evolutionary Mixture-of-Experts for SSVEP-EEG Classification With User-Independent Training
EvoMoE: Evolutionary Mixture-of-Experts for SSVEP-EEG Classification With User-Independent Training Open
The analysis of EEG data in BCI systems captures unique individual characteristics, presenting diverse patterns that deviate from conventional identical distribution assumptions. Therefore, applying AI models directly to brain data becomes…
View article: TRAIT: A Comprehensive Database for T-cell Receptor–antigen Interactions
TRAIT: A Comprehensive Database for T-cell Receptor–antigen Interactions Open
Comprehensive and integrated resources on interactions between T-cell receptors (TCRs) and antigens are still lacking for adoptive T-cell-based immunotherapies, highlighting a significant gap that must be addressed to fully understand the …
View article: EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting
EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting Open
High Dynamic Range (HDR) video reconstruction seeks to accurately restore the extensive dynamic range present in real-world scenes and is widely employed in downstream applications. Existing methods typically operate on one or a small numb…
View article: EvHDR-NeRF: Building High Dynamic Range Radiance Fields with Single Exposure Images and Events
EvHDR-NeRF: Building High Dynamic Range Radiance Fields with Single Exposure Images and Events Open
We present EvHDR-NeRF to recover a High Dynamic Range (HDR) radiance field from event streams and a set of Low Dynamic Range (LDR) views with single exposures. Using the EvHDR-NeRF, we can generate both novel HDR views and novel LDR views …
View article: Personalized Sleep Staging Leveraging Source-free Unsupervised Domain Adaptation
Personalized Sleep Staging Leveraging Source-free Unsupervised Domain Adaptation Open
Sleep staging is important for monitoring sleep quality and diagnosing sleep-related disorders. Recently, numerous deep learning-based models have been proposed for automatic sleep staging using polysomnography recordings. Most of them are…
View article: EvSTVSR: Event Guided Space-Time Video Super-Resolution
EvSTVSR: Event Guided Space-Time Video Super-Resolution Open
In the domain of space-time video super-resolution, it is typically challenging to handle complex motions (including large and nonlinear motions) and varying illumination scenes due to the lack of inter-frame information. Leveraging the de…
View article: MitraClip combined with PTSBME for the treatment of obstructive hypertrophic cardiomyopathy with severe mitral regurgitation: a case report
MitraClip combined with PTSBME for the treatment of obstructive hypertrophic cardiomyopathy with severe mitral regurgitation: a case report Open
Traditionally, both interventricular septal and mitral valve lesions are treated simultaneously through surgical intervention. However, the surgical conditions are relatively strict, and many patients are unable to undergo surgical treatme…
View article: Implantable Neural Probes with Monolithically Integrated CNTFET Arrays for Multimodal Monitoring
Implantable Neural Probes with Monolithically Integrated CNTFET Arrays for Multimodal Monitoring Open
The long-term implantable neural probe for simultaneous recording of various brain signals is the key technology of neuro clinic applications that needs to be broken through. This paper introduces carbon nanotube field-effect transistor (C…
View article: Linear Model of RIS-Aided High-Mobility Communication System
Linear Model of RIS-Aided High-Mobility Communication System Open
Reconfigurable intelligent surface (RIS)-aided vehicle-to-everything (V2X) communication has emerged as a crucial solution for providing reliable data services to vehicles on the road. However, in delay-sensitive or high-mobility communica…
View article: Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency
Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency Open
The human brain utilizes spikes for information transmission and dynamically reorganizes its network structure to boost energy efficiency and cognitive capabilities throughout its lifespan. Drawing inspiration from this spike-based computa…
View article: Spiking Neural Networks for Temporal Processing: Status Quo and Future Prospects
Spiking Neural Networks for Temporal Processing: Status Quo and Future Prospects Open
Temporal processing is fundamental for both biological and artificial intelligence systems, as it enables the comprehension of dynamic environments and facilitates timely responses. Spiking Neural Networks (SNNs) excel in handling such dat…
View article: Bio-plausible reconfigurable spiking neuron for neuromorphic computing
Bio-plausible reconfigurable spiking neuron for neuromorphic computing Open
Biological neurons use diverse temporal expressions of spikes to achieve efficient communication and modulation of neural activities. Nonetheless, existing neuromorphic computing systems mainly use simplified neuron models with limited spi…