Publications (39)
Continuous-Time Digital Twin with Analogue Memristive Neural Ordinary Differential Equation Solver
Hegan Chen, Jichang Yang, Jia Chen +20
Digital twins, the cornerstone of Industry 4.0, replicate real-world entities through computer models, revolutionising fields such as manufacturing management and industrial automa…
Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?
Jiacheng Cen, Anyi Li, Ning Lin +3
Equivariant Graph Neural Networks (GNNs) that incorporate E(3) symmetry have achieved significant success in various scientific applications. As one of the most successful models,…
Efficient lattice field theory simulation using adaptive normalizing flow on a resistive memory-based neural differential equation solver
Meng Xu, Jichang Yang, Ning Lin +6
Lattice field theory (LFT) simulations underpin advances in classical statistical mechanics and quantum field theory, providing a unified computational framework across particle, n…
SeDA: Secure and Efficient DNN Accelerators with Hardware/Software Synergy
Wei Xuan, Zhongrui Wang, Lang Feng +6
Ensuring the confidentiality and integrity of DNN accelerators is paramount across various scenarios spanning autonomous driving, healthcare, and finance. However, current security…
Universally Invariant Learning in Equivariant GNNs
Jiacheng Cen, Anyi Li, Ning Lin +5
Equivariant Graph Neural Networks (GNNs) have demonstrated significant success across various applications. To achieve completeness -- that is, the universal approximation property…
RNC: Efficient RRAM-aware NAS and Compilation for DNNs on Resource-Constrained Edge Devices
Kam Chi Loong, Shihao Han, Sishuo Liu +2
Computing-in-memory (CIM) is an emerging computing paradigm, offering noteworthy potential for accelerating neural networks with high parallelism, low latency, and energy efficienc…
Planar Symmetric Pattern Generation
Ning Lin, Luxi Chen, Huaguan Chen +4
Generating objects with specific symmetries is essential in various real-world scenarios. However, adapting existing 2D continuous representations to enforce planar group symmetry…
Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model
Jichang Yang, Hegan Chen, Jia Chen +19
Human brains image complicated scenes when reading a novel. Replicating this imagination is one of the ultimate goals of AI-Generated Content (AIGC). However, current AIGC methods,…
Random resistive memory-based deep extreme point learning machine for unified visual processing
Shaocong Wang, Yizhao Gao, Yi Li +21
Visual sensors, including 3D LiDAR, neuromorphic DVS sensors, and conventional frame cameras, are increasingly integrated into edge-side intelligent machines. Realizing intensive m…
Hazard resistance-based spatiotemporal risk analysis for distribution network outages during hurricanes
Luo Xu, Ning Lin, Dazhi Xi +2
Blackouts in recent decades show an increasing prevalence of power outages due to extreme weather events such as hurricanes. Precisely assessing the spatiotemporal outages in distr…
Dynamic neural network with memristive CIM and CAM for 2D and 3D vision
Yue Zhang, Woyu Zhang, Shaocong Wang +14
The brain is dynamic, associative and efficient. It reconfigures by associating the inputs with past experiences, with fused memory and processing. In contrast, AI models are stati…
Parameter Efficient Machine Unlearning on Hybrid Resistive Memory based Compute-in-Memory Accelerators
Ning Lin, Jichang Yang, Yangu He +17
Resistive memory compute-in-memory accelerators provide energy efficient analogue matrix vector multiplication for neural network inference, but frequent reprogramming of analogue…
Nowcast3D: Reliable precipitation nowcasting via gray-box learning
Huaguan Chen, Wei Han, Haofei Sun +9
Reliable nowcasting of extreme precipitation remains difficult because convective systems are strongly nonlinear, multiscale, and nonstationary in 3D. Radar is the backbone of nowc…
Reconfigurable Digital RRAM Logic Enables In-Situ Pruning and Learning for Edge AI
Songqi Wang, Yue Zhang, Jia Chen +9
The human brain simultaneously optimizes synaptic weights and topology by growing, pruning, and strengthening synapses while performing all computation entirely in memory. In contr…
Resistive memory-based zero-shot liquid state machine for multimodal event data learning
Ning Lin, Shaocong Wang, Yi Li +19
The human brain is a complex spiking neural network (SNN), capable of learning multimodal signals in a zero-shot manner by generalizing existing knowledge. Remarkably, it maintains…
Topology Optimization of Random Memristors for Input-Aware Dynamic SNN
Bo Wang, Shaocong Wang, Ning Lin +12
There is unprecedented development in machine learning, exemplified by recent large language models and world simulators, which are artificial neural networks running on digital co…
Efficient and accurate neural field reconstruction using resistive memory
Yifei Yu, Shaocong Wang, Woyu Zhang +16
Human beings construct perception of space by integrating sparse observations into massively interconnected synapses and neurons, offering a superior parallelism and efficiency. Re…
Pruning random resistive memory for optimizing analogue AI
Yi Li, Songqi Wang, Yaping Zhao +17
The rapid advancement of artificial intelligence (AI) has been marked by the large language models exhibiting human-like intelligence. However, these models also present unpreceden…
PACT: Peak-Aware Cross-Attention Graph Transformers for Efficient Storm-Surge Emulation
Zesheng Liu, Doyup Kwon, Ning Lin +1
Accurate and efficient storm-surge emulation is essential for coastal hazard assessment, yet high-fidelity hydrodynamic models remain too expensive for large scenario ensembles and…
Tetris: Re-architecting Convolutional Neural Network Computation for Machine Learning Accelerators
Hang Lu, Xin Wei, Ning Lin +2
Inference efficiency is the predominant consideration in designing deep learning accelerators. Previous work mainly focuses on skipping zero values to deal with remarkable ineffect…
Second-order continuous-time non-stationary Gaussian autoregression
Ning Lin, Sergey V. Lototsky
The objective of the paper is to identify and investigate all possible types of asymptotic behavior for the maximum likelihood estimators of the unknown parameters in the second-or…
Data-driven solar forecasting enables near-optimal economic decisions
Zhixiang Dai, Minghao Yin, Xuanhong Chen +27
Solar energy adoption is critical to achieving net-zero emissions. However, it remains difficult for many industrial and commercial actors to decide on whether they should adopt di…
SNNGX: Securing Spiking Neural Networks with Genetic XOR Encryption on RRAM-based Neuromorphic Accelerator
Kwunhang Wong, Songqi Wang, Wei Huang +8
Biologically plausible Spiking Neural Networks (SNNs), characterized by spike sparsity, are growing tremendous attention over intellectual edge devices and critical bio-medical app…
Quantifying cascading power outages during climate extremes considering renewable energy integration
Luo Xu, Ning Lin, H. Vincent Poor +2
Climate extremes, such as hurricanes, combined with large-scale integration of environment-sensitive renewables, could exacerbate the risk of widespread power outages. We introduce…
Hurricane-blackout-heatwave Compound Hazard Risk and Resilience in a Changing Climate
Kairui Feng, Ouyang Min, Ning Lin
Hurricanes have caused power outages and blackouts, affecting millions of customers and inducing severe social and economic impacts. The impacts of hurricane-caused blackouts may w…
SlotPi: Physics-informed Object-centric Reasoning Models
Jian Li, Wan Han, Ning Lin +8
Understanding and reasoning about dynamics governed by physical laws through visual observation, akin to human capabilities in the real world, poses significant challenges. Current…
DTC: Real-Time and Accurate Distributed Triangle Counting in Fully Dynamic Graph Streams
Wei Xuan, Yan Liang, Huawei Cao +3
Triangle counting is a fundamental problem in graph mining, essential for analyzing graph streams with arbitrary edge orders. However, exact counting becomes impractical due to the…
A reconstruction of Florida Traffic Flow During Hurricane Irma (2017)
Kairui Feng, Ning Lin
Recent Hurricane Irma (2017) created the most extensive scale of evacuation in Florida's history, involving about 6.5 million people on mandatory evacuation order and 4 million eva…
RRAM-DP: Device-Calibrated Differential Privacy for In-Memory Edge Learning
Kwunhang Wong, Jichang Yang, Karl M. H. Lai +7
Edge Artificial Intelligence of Things (AIoT) systems often collect sensitive data in situ, raising serious privacy concerns. Resistive-switching random-access memory (RRAM) is an…
Optimization and Generation in Aerodynamics Inverse Design
Huaguan Chen, Ning Lin, Luxi Chen +5
Aerodynamic inverse design can improve vehicle and aircraft efficiency, but practical design rarely seeks performance alone: vehicle refinement must reduce drag while preserving vi…
When Pipelined In-Memory Accelerators Meet Spiking Direct Feedback Alignment: A Co-Design for Neuromorphic Edge Computing
Haoxiong Ren, Yangu He, Kwunhang Wong +4
Spiking Neural Networks (SNNs) are increasingly favored for deployment on resource-constrained edge devices due to their energy-efficient and event-driven processing capabilities.…
Older and Wiser: The Marriage of Device Aging and Intellectual Property Protection of Deep Neural Networks
Ning Lin, Shaocong Wang, Yue Zhang +6
Deep neural networks (DNNs), such as the widely-used GPT-3 with billions of parameters, are often kept secret due to high training costs and privacy concerns surrounding the data u…
EvoCorps: An Evolutionary Multi-Agent Framework for Depolarizing Online Discourse
Ning Lin, Haolun Li, Mingshu Liu +5
Polarization in online discourse erodes social trust and accelerates misinformation, yet technical responses remain largely diagnostic and post-hoc. Current governance approaches s…
Tropical Cyclone Intensity Evolution Modeled as a Dependent Hidden Markov Process
Renzhi Jing, Ning Lin
A hidden Markov model is developed to simulate tropical cyclone intensity evolution dependent on the surrounding large-scale environment. The model considers three unobserved (hidd…
Situational Preparedness Dynamics for Sequential Tropical Cyclone Hazards
Tianle Duan, Qingchun Li, Fengxiu Zhang +2
Sequential tropical cyclone hazards--two tropical cyclones (TCs) making landfall in the same region within a short time--are becoming increasingly likely. This study investigates s…
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization
Yujie Zhou, Wenwen Qiang, Anyi Rao +3
Zero-shot skeleton-based action recognition aims to recognize actions of unseen categories after training on data of seen categories. The key is to build the connection between vis…
Towards Secure and Efficient DNN Accelerators via Hardware-Software Co-Design
Wei Xuan, Zihao Xuan, Rongliang Fu +8
The rapid deployment of deep neural network (DNN) accelerators in safety-critical domains such as autonomous vehicles, healthcare systems, and financial infrastructure necessitates…
Rapid Assessment of Damaged Homes in the Florida Keys after Hurricane Irma
Siyuan Xian, Kairui Feng, Ning Lin +4
On September 10, 2017, Hurricane Irma made landfall in the Florida Keys and caused significant damage. Informed by hydrodynamic storm surge and wave modeling and post-storm satelli…
Out-of-Distribution Generalized Dynamic Graph Neural Network for Human Albumin Prediction
Zeyang Zhang, Xingwang Li, Fei Teng +4
Human albumin is essential for indicating the body's overall health. Accurately predicting plasma albumin levels and determining appropriate doses are urgent clinical challenges, p…