papers

Publications (118)

cs.LG2025

CausalCOMRL: Context-Based Offline Meta-Reinforcement Learning with Causal Representation

Zhengzhe Zhang, Wenjia Meng, Haoliang Sun +1

Context-based offline meta-reinforcement learning (OMRL) methods have achieved appealing success by leveraging pre-collected offline datasets to develop task representations that g…

cs.LG2024

Off-OAB: Off-Policy Policy Gradient Method with Optimal Action-Dependent Baseline

Wenjia Meng, Qian Zheng, Long Yang +2

Policy-based methods have achieved remarkable success in solving challenging reinforcement learning problems. Among these methods, off-policy policy gradient methods are particular…

cs.NE2019

Unsupervised AER Object Recognition Based on Multiscale Spatio-Temporal Features and Spiking Neurons

Qianhui Liu, Gang Pan, Haibo Ruan +3

This paper proposes an unsupervised address event representation (AER) object recognition approach. The proposed approach consists of a novel multiscale spatio-temporal feature (Mu…

eess.SP2019

Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces

Yu Qi, Bin Liu, Yueming Wang +1

Brain-computer interfaces (BCIs) have enabled prosthetic device control by decoding motor movements from neural activities. Neural signals recorded from cortex exhibit nonstationar…

cs.LG2019

Field-aware Neural Factorization Machine for Click-Through Rate Prediction

Li Zhang, Weichen Shen, Shijian Li +1

Recommendation systems and computing advertisements have gradually entered the field of academic research from the field of commercial applications. Click-through rate prediction i…

cs.LG2018

State Distribution-aware Sampling for Deep Q-learning

Weichao Li, Fuxian Huang, Xi Li +2

A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample effici…

cs.CV2024

LOGO: Video Text Spotting with Language Collaboration and Glyph Perception Model

Hongen Liu, Di Sun, Jiahao Wang +2

Video text spotting (VTS) aims to simultaneously localize, recognize and track text instances in videos. To address the limited recognition capability of end-to-end methods, recent…

cs.AI2025

VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making

Zuojin Tang, Bin Hu, Chenyang Zhao +3

Recent large pretrained models such as LLMs (e.g., GPT series) and VLAs (e.g., OpenVLA) have achieved notable progress on multimodal tasks, yet they are built upon a multi-input si…

cs.LG2024

Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directions

Yangfan Hu, Qian Zheng, Guoqi Li +2

Deep learning has revolutionized artificial intelligence (AI), achieving remarkable progress in fields such as computer vision, speech recognition, and natural language processing.…

cs.LG2022

CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning

Long Yang, Jiaming Ji, Juntao Dai +3

Safe reinforcement learning (RL) is still very challenging since it requires the agent to consider both return maximization and safe exploration. In this paper, we propose CUP, a C…

eess.SP2025

CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding

Jiquan Wang, Sha Zhao, Zhiling Luo +5

Electroencephalography (EEG) is a non-invasive technique to measure and record brain electrical activity, widely used in various BCI and healthcare applications. Early EEG decoding…

cs.CV2024

A Framework For Image Synthesis Using Supervised Contrastive Learning

Yibin Liu, Jianyu Zhang, Li Zhang +2

Text-to-image (T2I) generation aims at producing realistic images corresponding to text descriptions. Generative Adversarial Network (GAN) has proven to be successful in this task.…

cs.AI2018

A Unified Approach for Multi-step Temporal-Difference Learning with Eligibility Traces in Reinforcement Learning

Long Yang, Minhao Shi, Qian Zheng +2

Recently, a new multi-step temporal learning algorithm, called , unifies -step Tree-Backup (when ) and -step Sarsa (when ) by introducing a sampling parame…

cs.LG2024

Personalized Sleep Staging Leveraging Source-free Unsupervised Domain Adaptation

Yangxuan Zhou, Sha Zhao, Jiquan Wang +5

Sleep staging is crucial for assessing sleep quality and diagnosing related disorders. Recent deep learning models for automatic sleep staging using polysomnography often suffer fr…

cs.CV2026

SleepVLM: A Rule-Grounded Vision-Language Model for Auditable Sleep Staging

Guifeng Deng, Pan Wang, Mengfan Niu +9

Sleep staging is essential for sleep assessment and disorder diagnosis. In recent years, automatic sleep staging systems have achieved accuracy approaching that of human experts, b…

cs.AI2025

SPICED: A Synaptic Homeostasis-Inspired Framework for Unsupervised Continual EEG Decoding

Yangxuan Zhou, Sha Zhao, Jiquan Wang +4

Human brain achieves dynamic stability-plasticity balance through synaptic homeostasis. Inspired by this biological principle, we propose SPICED: a neuromorphic framework that inte…

cs.NE2023

Biologically inspired structure learning with reverse knowledge distillation for spiking neural networks

Qi Xu, Yaxin Li, Xuanye Fang +4

Spiking neural networks (SNNs) have superb characteristics in sensory information recognition tasks due to their biological plausibility. However, the performance of some current s…

cs.NE2023

Darwin3: A large-scale neuromorphic chip with a Novel ISA and On-Chip Learning

De Ma, Xiaofei Jin, Shichun Sun +8

Spiking Neural Networks (SNNs) are gaining increasing attention for their biological plausibility and potential for improved computational efficiency. To match the high spatial-tem…

cs.LG2022

TinyLight: Adaptive Traffic Signal Control on Devices with Extremely Limited Resources

Dong Xing, Qian Zheng, Qianhui Liu +1

Recent advances in deep reinforcement learning (DRL) have largely promoted the performance of adaptive traffic signal control (ATSC). Nevertheless, regarding the implementation, mo…

eess.IV2024

Multi-Depth Branch Network for Efficient Image Super-Resolution

Huiyuan Tian, Li Zhang, Shijian Li +2

A longstanding challenge in Super-Resolution (SR) is how to efficiently enhance high-frequency details in Low-Resolution (LR) images while maintaining semantic coherence. This is p…

cs.HC2023

A Human-Machine Joint Learning Framework to Boost Endogenous BCI Training

Hanwen Wang, Yu Qi, Lin Yao +3

Brain-computer interfaces (BCIs) provide a direct pathway from the brain to external devices and have demonstrated great potential for assistive and rehabilitation technologies. En…

cs.LG2024

Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree

Lang Feng, Pengjie Gu, Bo An +1

Diffusion planners have shown promise in handling long-horizon and sparse-reward tasks due to the non-autoregressive plan generation. However, their inherent stochastic risk of gen…

cs.AI2026

EvoBrain: Continual Learning of EEG Foundation Models Across Heterogeneous BCI Tasks

Yangxuan Zhou, Sha Zhao, Jiquan Wang +2

Electroencephalography (EEG) is the cornerstone of non-invasive brain-computer interfaces (BCIs), yet conventional decoding relies on fragmented, task-specific architectures that s…

cs.CV2025

Hybrid Spiking Vision Transformer for Object Detection with Event Cameras

Qi Xu, Jie Deng, Jiangrong Shen +3

Event-based object detection has gained increasing attention due to its advantages such as high temporal resolution, wide dynamic range, and asynchronous address-event representati…

cs.NE2020

Effective AER Object Classification Using Segmented Probability-Maximization Learning in Spiking Neural Networks

Qianhui Liu, Haibo Ruan, Dong Xing +2

Address event representation (AER) cameras have recently attracted more attention due to the advantages of high temporal resolution and low power consumption, compared with traditi…

cs.CV2024

Spin-UP: Spin Light for Natural Light Uncalibrated Photometric Stereo

Zongrui Li, Zhan Lu, Haojie Yan +4

Natural Light Uncalibrated Photometric Stereo (NaUPS) relieves the strict environment and light assumptions in classical Uncalibrated Photometric Stereo (UPS) methods. However, due…

cs.LG2020

Sample Complexity of Policy Gradient Finding Second-Order Stationary Points

Long Yang, Qian Zheng, Gang Pan

The goal of policy-based reinforcement learning (RL) is to search the maximal point of its objective. However, due to the inherent non-concavity of its objective, convergence to a…

cs.CV2024

Semi-Supervised Pipe Video Temporal Defect Interval Localization

Zhu Huang, Gang Pan, Chao Kang +1

In sewer pipe Closed-Circuit Television (CCTV) inspection, accurate temporal defect localization is essential for effective defect classification, detection, segmentation and quant…

cs.CV2026

Neural-Driven Image Editing

Pengfei Zhou, Jie Xia, Xiaopeng Peng +15

Traditional image editing typically relies on manual prompting, making it labor-intensive and inaccessible to individuals with limited motor control or language abilities. Leveragi…

cs.ET2025

DarwinWafer: A Wafer-Scale Neuromorphic Chip

Xiaolei Zhu, Xiaofei Jin, Ziyang Kang +11

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, und…

cs.CV2025

PP-FormulaNet: Bridging Accuracy and Efficiency in Advanced Formula Recognition

Hongen Liu, Cheng Cui, Yuning Du +2

Formula recognition is an important task in document intelligence. It involves converting mathematical expressions from document images into structured symbolic formats that comput…

cs.HC2024

Copiloting Diagnosis of Autism in Real Clinical Scenarios via LLMs

Yi Jiang, Qingyang Shen, Shuzhong Lai +5

Autism spectrum disorder(ASD) is a pervasive developmental disorder that significantly impacts the daily functioning and social participation of individuals. Despite the abundance…

cs.ET2024

Roadmap for Unconventional Computing with Nanotechnology

Giovanni Finocchio, Jean Anne C. Incorvia, Joseph S. Friedman +48

In the "Beyond Moore's Law" era, with increasing edge intelligence, domain-specific computing embracing unconventional approaches will become increasingly prevalent. At the same ti…

cs.NE2020

Spiking Deep Residual Network

Yangfan Hu, Huajin Tang, Gang Pan

Spiking neural networks (SNNs) have received significant attention for their biological plausibility. SNNs theoretically have at least the same computational power as traditional a…

cs.LG2025

Efficient ANN-SNN Conversion with Error Compensation Learning

Chang Liu, Jiangrong Shen, Xuming Ran +4

Artificial neural networks (ANNs) have demonstrated outstanding performance in numerous tasks, but deployment in resource-constrained environments remains a challenge due to their…

cs.SE2024

Darkit: A User-Friendly Software Toolkit for Spiking Large Language Model

Xin Du, Shifan Ye, Qian Zheng +7

Large language models (LLMs) have been widely applied in various practical applications, typically comprising billions of parameters, with inference processes requiring substantial…

cs.CV2015

Robust Face Recognition by Constrained Part-based Alignment

Yuting Zhang, Kui Jia, Yueming Wang +3

Developing a reliable and practical face recognition system is a long-standing goal in computer vision research. Existing literature suggests that pixel-wise face alignment is the…

cs.CV2024

LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition

Jinyuan Li, Han Li, Di Sun +4

Grounded Multimodal Named Entity Recognition (GMNER) is a nascent multimodal task that aims to identify named entities, entity types and their corresponding visual regions. GMNER t…

cs.LG2022

Constrained Update Projection Approach to Safe Policy Optimization

Long Yang, Jiaming Ji, Juntao Dai +5

Safe reinforcement learning (RL) studies problems where an intelligent agent has to not only maximize reward but also avoid exploring unsafe areas. In this study, we propose CUP, a…

cs.CV2025

VP-MEL: Visual Prompts Guided Multimodal Entity Linking

Hongze Mi, Jinyuan Li, Xuying Zhang +4

Multimodal entity linking (MEL), a task aimed at linking mentions within multimodal contexts to their corresponding entities in a knowledge base (KB), has attracted much attention…

cs.NE2024

An Asynchronous Multi-core Accelerator for SNN inference

Zhuo Chen, De Ma, Xiaofei Jin +5

Spiking Neural Networks (SNNs) are extensively utilized in brain-inspired computing and neuroscience research. To enhance the speed and energy efficiency of SNNs, several many-core…

cs.LG2020

FiDi-RL: Incorporating Deep Reinforcement Learning with Finite-Difference Policy Search for Efficient Learning of Continuous Control

Longxiang Shi, Shijian Li, Longbing Cao +3

In recent years significant progress has been made in dealing with challenging problems using reinforcement learning.Despite its great success, reinforcement learning still faces c…

cs.MM2025

Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation

Jinyuan Li, Ziyan Li, Han Li +4

Grounded Multimodal Named Entity Recognition (GMNER) task aims to identify named entities, entity types and their corresponding visual regions. GMNER task exhibits two challenging…

cs.LG2025

Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization

Juntao Dai, Taiye Chen, Yaodong Yang +2

Reinforcement learning from human feedback (RLHF) is an effective method for aligning large language models (LLMs) with human values. However, reward over-optimization remains an o…

cs.LG2025

EMOD: A Unified EEG Emotion Representation Framework Leveraging V-A Guided Contrastive Learning

Yuning Chen, Sha Zhao, Shijian Li +1

Emotion recognition from EEG signals is essential for affective computing and has been widely explored using deep learning. While recent deep learning approaches have achieved stro…

cs.LG2025

EEGAgent: A Unified Framework for Automated EEG Analysis Using Large Language Models

Sha Zhao, Mingyi Peng, Haiteng Jiang +3

Scalable and generalizable analysis of brain activity is essential for advancing both clinical diagnostics and cognitive research. Electroencephalography (EEG), a non-invasive moda…

cs.AI2019

Monte Carlo Neural Fictitious Self-Play: Approach to Approximate Nash equilibrium of Imperfect-Information Games

Li Zhang, Wei Wang, Shijian Li +1

Researchers on artificial intelligence have achieved human-level intelligence in large-scale perfect-information games, but it is still a challenge to achieve (nearly) optimal resu…

cs.CV2026

ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos

Peijun Bao, Anwei Luo, Gang Pan +2

Temporal forgery localization aims to temporally identify manipulated segments in videos. Most existing benchmarks focus on appearance-level forgeries, such as face swapping and ob…

cs.LG2019

Gradient Q: A Unified Algorithm with Function Approximation for Reinforcement Learning

Long Yang, Yu Zhang, Qian Zheng +2

Full-sampling (e.g., Q-learning) and pure-expectation (e.g., Expected Sarsa) algorithms are efficient and frequently used techniques in reinforcement learning. Q is the fi…

cs.NE2023

Multi-Level Firing with Spiking DS-ResNet: Enabling Better and Deeper Directly-Trained Spiking Neural Networks

Lang Feng, Qianhui Liu, Huajin Tang +2

Spiking neural networks (SNNs) are bio-inspired neural networks with asynchronous discrete and sparse characteristics, which have increasingly manifested their superiority in low e…

cs.NE2023

ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks

Jiangrong Shen, Qi Xu, Jian K. Liu +3

Spiking neural networks (SNNs) have manifested remarkable advantages in power consumption and event-driven property during the inference process. To take full advantage of low powe…

cs.NE2025

Bridging Quantized Artificial Neural Networks and Neuromorphic Hardware

Zhenhui Chen, Haoran Xu, Yangfan Hu +5

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 s…

cs.NE2024

LitE-SNN: Designing Lightweight and Efficient Spiking Neural Network through Spatial-Temporal Compressive Network Search and Joint Optimization

Qianhui Liu, Jiaqi Yan, Malu Zhang +2

Spiking Neural Networks (SNNs) mimic the information-processing mechanisms of the human brain and are highly energy-efficient, making them well-suited for low-power edge devices. H…

cs.AI2026

BrainBench: Benchmarking Large Language Models for Comprehensive EEG Understanding

Yangxuan Zhou, Sha Zhao, Yuning Chen +4

Electroencephalography (EEG) analysis extends beyond assigning predefined labels to recordings; it requires workflows connecting natural-language instructions, signal processing, q…

cs.LG2024

Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation

Juntao Dai, Yaodong Yang, Qian Zheng +1

A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy…

cs.LG2019

Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network

Wenjia Meng, Qian Zheng, Long Yang +2

The deep Q-network (DQN) and return-based reinforcement learning are two promising algorithms proposed in recent years. DQN brings advances to complex sequential decision problems,…

cs.RO2026

ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models

Zuojin Tang, Haoyun Liu, Xinyuan Chang +11

Vision-language-action (VLA) models remain constrained by the scarcity of action-labeled robot data, whereas action-free videos provide abundant evidence of how the physical world…

cs.DC2025

FpgaHub: Fpga-centric Hyper-heterogeneous Computing Platform for Big Data Analytics

Zeke Wang, Jie Zhang, Hongjing Huang +10

Modern data analytics requires a huge amount of computing power and processes a massive amount of data. At the same time, the underlying computing platform is becoming much more he…

cs.NE2024

Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks

Qi Xu, Yuyuan Gao, Jiangrong Shen +4

Spiking neural networks (SNNs) serve as one type of efficient model to process spatio-temporal patterns in time series, such as the Address-Event Representation data collected from…

cs.CV2022

NeIF: Representing General Reflectance as Neural Intrinsics Fields for Uncalibrated Photometric Stereo

Zongrui Li, Qian Zheng, Feishi Wang +3

Uncalibrated photometric stereo (UPS) is challenging due to the inherent ambiguity brought by unknown light. Existing solutions alleviate the ambiguity by either explicitly associa…

cs.LG2026

DeeperBrain: A Neuro-Grounded EEG Foundation Model Towards Universal BCI

Jiquan Wang, Sha Zhao, Yangxuan Zhou +3

Electroencephalography (EEG) foundation models hold significant promise for universal Brain-Computer Interfaces (BCIs). However, existing approaches often rely on end-to-end fine-t…

cs.CV2024

Rethinking Sampling Strategies for Unsupervised Person Re-identification

Xumeng Han, Xuehui Yu, Guorong Li +5

Unsupervised person re-identification (re-ID) remains a challenging task. While extensive research has focused on the framework design and loss function, this paper shows that samp…

cs.NE2025

Mitigating Communication Costs in Neural Networks: The Role of Dendritic Nonlinearity

Xundong Wu, Pengfei Zhao, Zilin Yu +6

Our understanding of biological neuronal networks has profoundly influenced the development of artificial neural networks (ANNs). However, neurons utilized in ANNs differ considera…

cs.AI2026

Otters++: A Time-to-first-spike Based Energy Efficient Optical Spiking Transformer

Zhanglu Yan, Jiayi Mao, Kaiwen Tang +6

Spiking neural networks (SNNs) are promising for energy-efficient inference, and time-to-first-spike (TTFS) coding is especially attractive because each neuron fires at most once.…

cs.CV2024

Spiking GS: Towards High-Accuracy and Low-Cost Surface Reconstruction via Spiking Neuron-based Gaussian Splatting

Weixing Zhang, Zongrui Li, De Ma +4

3D Gaussian Splatting is capable of reconstructing 3D scenes in minutes. Despite recent advances in improving surface reconstruction accuracy, the reconstructed results still exhib…

cs.CV2025

Sewer Image Super-Resolution with Depth Priors and Its Lightweight Network

Gang Pan, Chen Wang, Zhijie Sui +5

The Quick-view (QV) technique serves as a primary method for detecting defects within sewerage systems. However, the effectiveness of QV is impeded by the limited visual range of i…

cs.MA2023

Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification

Dong Xing, Pengjie Gu, Qian Zheng +5

Ad hoc teamwork requires an agent to cooperate with unknown teammates without prior coordination. Many works propose to abstract teammate instances into high-level representation o…

cs.DC2025

Edge Intelligence with Spiking Neural Networks

Shuiguang Deng, Di Yu, Changze Lv +10

The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditio…

cs.NE2021

Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN

Tao Fang, Yu Qi, Gang Pan

Reconstructing seeing images from fMRI recordings is an absorbing research area in neuroscience and provides a potential brain-reading technology. The challenge lies in that visual…

cs.AI2026

D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents

Hongze Mi, Yibo Feng, Wenjie Lu +12

Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by s…

eess.SP2026

Design and Validation of a Portable EEG-tES Platform Supporting High-Rate EEG Recording and Temporal Interference Stimulation

Le Xing, Maoxing Liang, Disi A +7

Background: Closed-loop neuromodulation integrating electroencephalography (EEG) and transcranial electrical stimulation (tES) has strong potential for neuroscience research and cl…

cs.CV2025

SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis

Huiyuan Tian, Bonan Xu, Shijian Li +1

Knowledge Distillation (KD) has achieved widespread success in compressing large Vision Transformers (ViTs), but a unified theoretical framework for both ViTs and KD is still lacki…

cs.NE2023

NeuSort: An Automatic Adaptive Spike Sorting Approach with Neuromorphic Models

Hang Yu, Yu Qi, Gang Pan

Objective. Spike sorting, a critical step in neural data processing, aims to classify spiking events from single electrode recordings based on different waveforms. This study aims…

cs.CL2026

Brain-CLIPLM: Semantic Compression for EEG-to-Text Decoding

Xiaoli Yang, Huiyuan Tian, Yurui Li +3

Decoding natural language from non-invasive electroencephalography (EEG) remains constrained by low signal-to-noise ratio and limited information bandwidth. This raises a central q…

cs.CV2026

EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection

Shuo Jiang, Gaojia Zhang, Min Tan +2

Unsupervised Camouflaged Object Detection (UCOD) remains a challenging task due to the high intrinsic similarity between target objects and their surroundings, as well as the relia…

cs.CV2024

Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation

Zhanfeng Liao, Qian Zheng, Yan Liu +1

A crucial reason for the success of existing NeRF-based methods is to build a neural density field for the geometry representation via multiple perceptron layers (MLPs). MLPs are c…

cs.LG2025

Otters: An Energy-Efficient SpikingTransformer via Optical Time-to-First-Spike Encoding

Zhanglu Yan, Jiayi Mao, Qianhui Liu +5

Spiking neural networks (SNNs) promise high energy efficiency, particularly with time-to-first-spike (TTFS) encoding, which maximizes sparsity by emitting at most one spike per neu…

cs.NE2018

Efficient Spiking Neural Networks with Logarithmic Temporal Coding

Ming Zhang, Nenggan Zheng, De Ma +2

A Spiking Neural Network (SNN) can be trained indirectly by first training an Artificial Neural Network (ANN) with the conventional backpropagation algorithm, then converting it in…

cs.CV2023

SceneCalib: Automatic Targetless Calibration of Cameras and Lidars in Autonomous Driving

Ayon Sen, Gang Pan, Anton Mitrokhin +1

Accurate camera-to-lidar calibration is a requirement for sensor data fusion in many 3D perception tasks. In this paper, we present SceneCalib, a novel method for simultaneous self…

cs.NE2022

SPAIC: A Spike-based Artificial Intelligence Computing Framework

Chaofei Hong, Mengwen Yuan, Mengxiao Zhang +6

Neuromorphic computing is an emerging research field that aims to develop new intelligent systems by integrating theories and technologies from multi-disciplines such as neuroscien…

q-bio.NC2023

Emergence and reconfiguration of modular structure for synaptic neural networks during continual familiarity detection

Shi Gu, Marcelo G Mattar, Huajin Tang +1

While advances in artificial intelligence and neuroscience have enabled the emergence of neural networks capable of learning a wide variety of tasks, our understanding of the tempo…

cs.LG2023

FP3O: Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility

Lang Feng, Dong Xing, Junru Zhang +1

Existing multi-agent PPO algorithms lack compatibility with different types of parameter sharing when extending the theoretical guarantee of PPO to cooperative multi-agent reinforc…

cs.LG2026

TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue

Shuzhong Lai, Junhong Lai, Chenxi Li +5

The sycophancy of large language models can increase the safety risk in intervention dialogue for autistic children. Supervised fine-tuning can somewhat reduce sycophancy, but rely…

cs.CV2023

MindGPT: Interpreting What You See with Non-invasive Brain Recordings

Jiaxuan Chen, Yu Qi, Yueming Wang +1

Decoding of seen visual contents with non-invasive brain recordings has important scientific and practical values. Efforts have been made to recover the seen images from brain sign…

cs.AI2021

Optimize Neural Fictitious Self-Play in Regret Minimization Thinking

Yuxuan Chen, Li Zhang, Shijian Li +1

Optimization of deep learning algorithms to approach Nash Equilibrium remains a significant problem in imperfect information games, e.g. StarCraft and poker. Neural Fictitious Self…

cs.LG2025

Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors

Lang Feng, Jiahao Lin, Dong Xing +3

Population-population generalization is a challenging problem in multi-agent reinforcement learning (MARL), particularly when agents encounter unseen co-players. However, existing…

cs.LG2025

CTC: The Composite Task Challenge for Cooperative Multi-Agent Reinforcement Learning

Yurui Li, Yuxuan Chen, Li Zhang +3

The critical role of division of labor (DOL) in enhancing cooperation is well-recognized in real-world applications. Consequently, many cooperative multi-agent reinforcement learni…

cs.CV2017

Spectral Sparse Representation for Clustering: Evolved from PCA, K-means, Laplacian Eigenmap, and Ratio Cut

Zhenfang Hu, Gang Pan, Yueming Wang +1

Dimensionality reduction, cluster analysis, and sparse representation are basic components in machine learning. However, their relationships have not yet been fully investigated. I…

cs.CV2023

DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering

Zongrui Li, Qian Zheng, Boxin Shi +2

Uncalibrated photometric stereo (UPS) is challenging due to the inherent ambiguity brought by the unknown light. Although the ambiguity is alleviated on non-Lambertian objects, the…

cs.NE2026

UniSpike: Accelerating Spiking Neural Networks on Neuromorphic Systems via Eliminating Address Redundancy

Qinghui Xing, Zhuo Chen, Xin Du +6

Many-core neuromorphic systems accelerate Spiking Neural Networks (SNNs), yet their packet-based spike communication can spend substantial traffic and energy repeatedly transmittin…

cs.CV2024

Enhancing SNN-based Spatio-Temporal Learning: A Benchmark Dataset and Cross-Modality Attention Model

Shibo Zhou, Bo Yang, Mengwen Yuan +4

Spiking Neural Networks (SNNs), renowned for their low power consumption, brain-inspired architecture, and spatio-temporal representation capabilities, have garnered considerable a…

q-bio.NC2019

Brain Network Construction and Classification Toolbox (BrainNetClass)

Zhen Zhou, Xiaobo Chen, Yu Zhang +5

Brain functional network has become an increasingly used approach in understanding brain functions and diseases. Many network construction methods have been developed, whereas the…

cs.LG2019

TBQ(): Improving Efficiency of Trace Utilization for Off-Policy Reinforcement Learning

Longxiang Shi, Shijian Li, Longbing Cao +2

Off-policy reinforcement learning with eligibility traces is challenging because of the discrepancy between target policy and behavior policy. One common approach is to measure the…

cs.HC2025

Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency

Jiangrong Shen, Qi Xu, Gang Pan +1

The human brain utilizes spikes for information transmission and dynamically reorganizes its network structure to boost energy efficiency and cognitive capabilities throughout its…

cs.NE2023

Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillation

Qi Xu, Yaxin Li, Jiangrong Shen +3

Spiking neural networks (SNNs) are well known as the brain-inspired models with high computing efficiency, due to a key component that they utilize spikes as information units, clo…

cs.AI2026

BrainAgent: A Large Language Model-Driven Multi-Agent Framework for Autonomous Brain Signal Understanding

Yangxuan Zhou, Sha Zhao, Jiquan Wang +2

Brain-Computer Interfaces (BCIs) and brain signal understanding are pivotal for clinical health and next-generation interactions. Despite this significance, its widespread adoption…

cs.SD2025

Wearable Music2Emotion : Assessing Emotions Induced by AI-Generated Music through Portable EEG-fNIRS Fusion

Sha Zhao, Song Yi, Yangxuan Zhou +6

Emotions critically influence mental health, driving interest in music-based affective computing via neurophysiological signals with Brain-computer Interface techniques. While prio…

cs.LG2021

Thompson Sampling for Unimodal Bandits

Long Yang, Zhao Li, Zehong Hu +4

In this paper, we propose a Thompson Sampling algorithm for \emph{unimodal} bandits, where the expected reward is unimodal over the partially ordered arms. To exploit the unimodal…

cs.NE2024

Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruning

Yaxin Li, Qi Xu, Jiangrong Shen +3

The emergence of deep and large-scale spiking neural networks (SNNs) exhibiting high performance across diverse complex datasets has led to a need for compressing network models du…

cs.NE2025

TS-SNN: Temporal Shift Module for Spiking Neural Networks

Kairong Yu, Tianqing Zhang, Qi Xu +2

Spiking Neural Networks (SNNs) are increasingly recognized for their biological plausibility and energy efficiency, positioning them as strong alternatives to Artificial Neural Net…