arXiv subjects

Shigang Chen

Publications and source records attributed to Shigang Chen.

18 recordsLinked to original sources

arXiv2026

EarthSpatialBench: Benchmarking Spatial Reasoning Capabilities of Multimodal LLMs on Earth Imagery

Benchmarking spatial reasoning in multimodal large language models (MLLMs) has attracted growing interest in computer vision due to its importance for embodied AI and other agentic systems that require precise interaction with the physical world. However, spatial reasoning on Earth imagery has lagged behind, as it uniquely involves grounding objects in georeferenced images and quantitatively reasoning about distances, directions, and topological relations using both visual cues and vector geometry coordinates (e.g., 2D bounding boxes, polylines, and polygons). Existing benchmarks for Earth imagery primarily focus on 2D spatial grounding, image captioning, and coarse spatial relations (e.g., simple directional or proximity cues). They lack support for quantitative direction and distance reasoning, systematic topological relations, and complex object geometries beyond bounding boxes. To fill this gap, we propose \textbf{EarthSpatialBench}, a comprehensive benchmark for evaluating spatial reasoning in MLLMs on Earth imagery. The benchmark contains over 325K question-answer pairs spanning: (1) qualitative and quantitative reasoning about spatial distance and direction; (2) systematic topological relations; (3) single-object queries, object-pair queries, and compositional aggregate group queries; and (4) object references expressed via textual descriptions, visual overlays, and explicit geometry coordinates, including 2D bounding boxes, polylines, and polygons. We conducted extensive experiments on both open-source and proprietary models to identify limitations in the spatial reasoning of MLLMs.

cs.CV↗

arXiv2026

VNU-Bench: A Benchmarking Dataset for Multi-Source Multimodal News Video Understanding

News videos are carefully edited multimodal narratives that combine narration, visuals, and external quotations into coherent storylines. In recent years, there have been significant advances in evaluating multimodal large language models (MLLMs) for news video understanding. However, existing benchmarks largely focus on single-source, intra-video reasoning, where each report is processed in isolation. In contrast, real-world news consumption is inherently multi-sourced: the same event is reported by different outlets with complementary details, distinct narrative choices, and sometimes conflicting claims that unfold over time. Robust news understanding, therefore, requires models to compare perspectives from different sources, align multimodal evidence across sources, and synthesize multi-source information. To fill this gap, we introduce VNU-Bench, the first benchmark for multi-source, cross-video understanding in the news domain. We design a set of new question types that are unique in testing models' ability of understanding multi-source multimodal news from a variety of different angles. We design a novel hybrid human-model QA generation process that addresses the issues of scalability and quality control in building a large dataset for cross-source news understanding. The dataset comprises 429 news groups, 1,405 videos, and 2,501 high-quality questions. Comprehensive evaluation of both closed- and open-source multimodal models shows that VNU-Bench poses substantial challenges for current MLLMs.

cs.LG↗

arXiv2025

Spatio-temporal Multivariate Time Series Forecast with Chosen Variables

Spatio-Temporal Multivariate time series Forecast (STMF) uses the time series of $n$ spatially distributed variables in a period of recent past to forecast their values in a period of near future. It has important applications in spatio-temporal sensing forecast such as road traffic prediction and air pollution prediction. Recent papers have addressed a practical problem of missing variables in the model input, which arises in the sensing applications where the number $m$ of sensors is far less than the number $n$ of locations to be monitored, due to budget constraints. We observe that the state of the art assumes that the $m$ variables (i.e., locations with sensors) in the model input are pre-determined and the important problem of how to choose the $m$ variables in the input has never been studied. This paper fills the gap by studying a new problem of STMF with chosen variables, which optimally selects $m$-out-of-$n$ variables for the model input in order to maximize the forecast accuracy. We propose a unified framework that jointly performs variable selection and model optimization for both forecast accuracy and model efficiency. It consists of three novel technical components: (1) masked variable-parameter pruning, which progressively prunes less informative variables and attention parameters through quantile-based masking; (2) prioritized variable-parameter replay, which replays low-loss past samples to preserve learned knowledge for model stability; (3) dynamic extrapolation mechanism, which propagates information from variables selected for the input to all other variables via learnable spatial embeddings and adjacency information. Experiments on five real-world datasets show that our work significantly outperforms the state-of-the-art baselines in both accuracy and efficiency, demonstrating the effectiveness of joint variable selection and model optimization.

cs.LG↗

arXiv2025

Morph: ChirpTransformer-based Encoder-decoder Co-design for Reliable LoRa Communication

In this paper, we propose Morph, a LoRa encoder-decoder co-design to enhance communication reliability while improving its computation efficiency in extremely-low signal-to-noise ratio (SNR) situations. The standard LoRa encoder controls 6 Spreading Factors (SFs) to tradeoff SNR tolerance with data rate. SF-12 is the maximum SF providing the lowest SNR tolerance on commercial off-the-shelf (COTS) LoRa nodes. In Morph, we develop an SF-configuration based encoder to mimic the larger SFs beyond SF-12 while it is compatible with COTS LoRa nodes. Specifically, we manipulate four SF configurations of a Morph symbol to encode 2-bit data. Accordingly, we recognize the used SF configuration of the symbol for data decoding. We leverage a Deep Neural Network (DNN) decoder to fully capture multi-dimensional features among diverse SF configurations to maximize the SNR gain. Moreover, we customize the input size, neural network structure, and training method of the DNN decoder to improve its efficiency, reliability, and generalizability. We implement Morph with COTS LoRa nodes and a USRP N210, then evaluate its performance on indoor and campus-scale testbeds. Results show that we can reliably decode data at -28.8~dB SNR, which is 6.4~dB lower than the standard LoRa with SF-12 chirps. In addition, the computation efficiency of our DNN decoder is about 3x higher than state-of-the-art.

cs.NI↗

arXiv2024

Accelerate Coastal Ocean Circulation Model with AI Surrogate

Nearly 900 million people live in low-lying coastal zones around the world and bear the brunt of impacts from more frequent and severe hurricanes and storm surges. Oceanographers simulate ocean current circulation along the coasts to develop early warning systems that save lives and prevent loss and damage to property from coastal hazards. Traditionally, such simulations are conducted using coastal ocean circulation models such as the Regional Ocean Modeling System (ROMS), which usually runs on an HPC cluster with multiple CPU cores. However, the process is time-consuming and energy expensive. While coarse-grained ROMS simulations offer faster alternatives, they sacrifice detail and accuracy, particularly in complex coastal environments. Recent advances in deep learning and GPU architecture have enabled the development of faster AI (neural network) surrogates. This paper introduces an AI surrogate based on a 4D Swin Transformer to simulate coastal tidal wave propagation in an estuary for both hindcast and forecast (up to 12 days). Our approach not only accelerates simulations but also incorporates a physics-based constraint to detect and correct inaccurate results, ensuring reliability while minimizing manual intervention. We develop a fully GPU-accelerated workflow, optimizing the model training and inference pipeline on NVIDIA DGX-2 A100 GPUs. Our experiments demonstrate that our AI surrogate reduces the time cost of 12-day forecasting of traditional ROMS simulations from 9,908 seconds (on 512 CPU cores) to 22 seconds (on one A100 GPU), achieving over 450$\times$ speedup while maintaining high-quality simulation results. This work contributes to oceanographic modeling by offering a fast, accurate, and physically consistent alternative to traditional simulation models, particularly for real-time forecasting in rapid disaster response.

cs.LG↗

arXiv2024

Multi-View Neural Differential Equations for Continuous-Time Stream Data in Long-Term Traffic Forecasting

Long-term traffic flow forecasting plays a crucial role in intelligent transportation as it allows traffic managers to adjust their decisions in advance. However, the problem is challenging due to spatio-temporal correlations and complex dynamic patterns in continuous-time stream data. Neural Differential Equations (NDEs) are among the state-of-the-art methods for learning continuous-time traffic dynamics. However, the traditional NDE models face issues in long-term traffic forecasting due to failures in capturing delayed traffic patterns, dynamic edge (location-to-location correlation) patterns, and abrupt trend patterns. To fill this gap, we propose a new NDE architecture called Multi-View Neural Differential Equations. Our model captures current states, delayed states, and trends in different state variables (views) by learning latent multiple representations within Neural Differential Equations. Extensive experiments conducted on several real-world traffic datasets demonstrate that our proposed method outperforms the state-of-the-art and achieves superior prediction accuracy for long-term forecasting and robustness with noisy or missing inputs.

cs.LG↗

arXiv2024

Spatio-Temporal Partial Sensing Forecast for Long-term Traffic

Traffic forecasting uses recent measurements by sensors installed at chosen locations to forecast the future road traffic. Existing work either assumes all locations are equipped with sensors or focuses on short-term forecast. This paper studies partial sensing forecast of long-term traffic, assuming sensors are available only at some locations. The problem is challenging due to the unknown data distribution at unsensed locations, the intricate spatio-temporal correlation in long-term forecasting, as well as noise to traffic patterns. We propose a Spatio-temporal Long-term Partial sensing Forecast model (SLPF) for traffic prediction, with several novel contributions, including a rank-based embedding technique to reduce the impact of noise in data, a spatial transfer matrix to overcome the spatial distribution shift from sensed locations to unsensed locations, and a multi-step training process that utilizes all available data to successively refine the model parameters for better accuracy. Extensive experiments on several real-world traffic datasets demonstrate its superior performance. Our source code is at https://github.com/zbliu98/SLPF

cs.LG↗

arXiv2024

XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications

Adverse clinical events related to unsafe care are among the top ten causes of death in the U.S. Accurate modeling and prediction of clinical events from electronic health records (EHRs) play a crucial role in patient safety enhancement. An example is modeling de facto care pathways that characterize common step-by-step plans for treatment or care. However, clinical event data pose several unique challenges, including the irregularity of time intervals between consecutive events, the existence of cycles, periodicity, multi-scale event interactions, and the high computational costs associated with long event sequences. Existing neural temporal point processes (TPPs) methods do not effectively capture the multi-scale nature of event interactions, which is common in many real-world clinical applications. To address these issues, we propose the cross-temporal-scale transformer (XTSFormer), specifically designed for irregularly timed event data. Our model consists of two vital components: a novel Feature-based Cycle-aware Time Positional Encoding (FCPE) that adeptly captures the cyclical nature of time, and a hierarchical multi-scale temporal attention mechanism, where different temporal scales are determined by a bottom-up clustering approach. Extensive experiments on several real-world EHR datasets show that our XTSFormer outperforms multiple baseline methods. The code is available at https://github.com/spatialdatasciencegroup/XTSFormer.

cs.LG↗

arXiv2023

A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Space

Transformers are widely used deep learning architectures. Existing transformers are mostly designed for sequences (texts or time series), images or videos, and graphs. This paper proposes a novel transformer model for massive (up to a million) point samples in continuous space. Such data are ubiquitous in environment sciences (e.g., sensor observations), numerical simulations (e.g., particle-laden flow, astrophysics), and location-based services (e.g., POIs and trajectories). However, designing a transformer for massive spatial points is non-trivial due to several challenges, including implicit long-range and multi-scale dependency on irregular points in continuous space, a non-uniform point distribution, the potential high computational costs of calculating all-pair attention across massive points, and the risks of over-confident predictions due to varying point density. To address these challenges, we propose a new hierarchical spatial transformer model, which includes multi-resolution representation learning within a quad-tree hierarchy and efficient spatial attention via coarse approximation. We also design an uncertainty quantification branch to estimate prediction confidence related to input feature noise and point sparsity. We provide a theoretical analysis of computational time complexity and memory costs. Extensive experiments on both real-world and synthetic datasets show that our method outperforms multiple baselines in prediction accuracy and our model can scale up to one million points on one NVIDIA A100 GPU. The code is available at \url{https://github.com/spatialdatasciencegroup/HST}.

cs.LG↗

arXiv2023

Reducing Noise Level in Differential Privacy through Matrix Masking

Differential privacy schemes have been widely adopted in recent years to address issues of data privacy protection. We propose a new Gaussian scheme combining with another data protection technique, called random orthogonal matrix masking, to achieve $(\varepsilon, δ)$-differential privacy (DP) more efficiently. We prove that the additional matrix masking significantly reduces the rate of noise variance required in the Gaussian scheme to achieve $(\varepsilon, δ)-$DP in big data setting. Specifically, when $\varepsilon \to 0$, $δ\to 0$, and the sample size $n$ exceeds the number $p$ of attributes by $(n-p)=O(ln(1/δ))$, the required additive noise variance to achieve $(\varepsilon, δ)$-DP is reduced from $O(ln(1/δ)/\varepsilon^2)$ to $O(1/\varepsilon)$. With much less noise added, the resulting differential privacy protected pseudo data sets allow much more accurate inferences, thus can significantly improve the scope of application for differential privacy.

cs.CR↗

arXiv2022

Digital Twin for Secure Semiconductor Lifecycle Management: Prospects and Applications

The expansive globalization of the semiconductor supply chain has introduced numerous untrusted entities into different stages of a device's lifecycle. To make matters worse, the increase complexity in the design as well as aggressive time to market requirements of the newer generation of integrated circuits can lead either designers to unintentionally introduce security vulnerabilities or verification engineers to fail in detecting them earlier in the design lifecycle. These overlooked or undetected vulnerabilities can be exploited by malicious entities in subsequent stages of the lifecycle through an ever widening variety of hardware attacks. The ability to ascertain the provenance of these vulnerabilities, therefore, becomes a pressing issue when the security assurance across the whole lifecycle is required to be ensured. We posit that if there is a malicious or unintentional breach of security policies of a device, it will be reflected in the form of anomalies in the traditional design, verification and testing activities throughout the lifecycle. With that, a digital simulacrum of a device's lifecycle, called a digital twin (DT), can be formed by the data gathered from different stages to secure the lifecycle of the device. In this paper, we put forward a realization of intertwined relationships of security vulnerabilities with data available from the silicon lifecycle and formulate different components of an AI driven DT framework. The proposed DT framework leverages these relationships and relational learning to achieve Forward and Backward Trust Analysis functionalities enabling security aware management of the entire lifecycle. Finally, we provide potential future research avenues and challenges for realization of the digital twin framework to enable secure semiconductor lifecycle management.

cs.CR↗

arXiv2017

Session-Based Cooperation in Cognitive Radio Networks: A Network-Level Approach

In cognitive radio networks (CRNs), secondary users (SUs) can proactively obtain spectrum access opportunities by helping with primary users' (PUs') data transmissions. Currently, such kind of spectrum access is implemented via a cooperative communications based link-level frame-based cooperative (LLC) approach where individual SUs independently serve as relays for PUs in order to gain spectrum access opportunities. Unfortunately, this LLC approach cannot fully exploit spectrum access opportunities to enhance the throughput of CRNs and fails to motivate PUs to join the spectrum sharing processes. To address these challenges, we propose a network-level session-based cooperative (NLC) approach where SUs are grouped together to cooperate with PUs session by session, instead of frame by frame as what has been done in existing works, for spectrum access opportunities of the corresponding group. Thanks to our group-based session-by-session cooperating strategy, our NLC approach is able to address all those challenges in the LLC approach. To articulate our NLC approach, we further develop an NLC scheme under a cognitive capacity harvesting network (CCHN) architecture. We formulate the cooperative mechanism design as a cross-layer optimization problem with constraints on primary session selection, flow routing and link scheduling. To search for solutions to the optimization problem, we propose an augmented scheduling index ordering based (SIO-based) algorithm to identify maximal independent sets. Through extensive simulations, we demonstrate the effectiveness of the proposed NLC approach and the superiority of the augmented SIO-based algorithm over the traditional method.

cs.IT↗

arXiv2017

Persistent Spread Measurement for Big Network Data Based on Register Intersection

Persistent spread measurement is to count the number of distinct elements that persist in each network flow for predefined time periods. It has many practical applications, including detecting long-term stealthy network activities in the background of normal-user activities, such as stealthy DDoS attack, stealthy network scan, or faked network trend, which cannot be detected by traditional flow cardinality measurement. With big network data, one challenge is to measure the persistent spreads of a massive number of flows without incurring too much memory overhead as such measurement may be performed at the line speed by network processors with fast but small on-chip memory. We propose a highly compact Virtual Intersection HyperLogLog (VI-HLL) architecture for this purpose. It achieves far better memory efficiency than the best prior work of V-Bitmap, and in the meantime drastically extends the measurement range. Theoretical analysis and extensive experiments demonstrate that VI-HLL provides good measurement accuracy even in very tight memory space of less than 1 bit per flow.

cs.NI↗

arXiv2016

Limiting Self-Propagating Malware Based on Connection Failure Behavior through Hyper-Compact Estimators

Self-propagating malware (e.g., an Internet worm) exploits security loopholes in software to infect servers and then use them to scan the Internet for more vulnerable servers. While the mechanisms of worm infection and their propagation models are well understood, defense against worms remains an open problem. One branch of defense research investigates the behavioral difference between worm-infected hosts and normal hosts to set them apart. One particular observation is that a worm-infected host, which scans the Internet with randomly selected addresses, has a much higher connection-failure rate than a normal host. Rate-limit algorithms have been proposed to control the spread of worms by traffic shaping based on connection failure rate. However, these rate-limit algorithms can work properly only if it is possible to measure failure rates of individual hosts efficiently and accurately. This paper points out a serious problem in the prior method. To address this problem, we first propose a solution based on a highly efficient double-bitmap data structure, which places only a small memory footprint on the routers, while providing good measurement of connection failure rates whose accuracy can be tuned by system parameters. Furthermore, we propose another solution based on shared register array data structure, achieving better memory efficiency and much larger estimation range than our double-bitmap solution.

cs.NI↗

arXiv2011

Analysis of Power-aware Buffering Schemes in Wireless Sensor Networks

We study the power-aware buffering problem in battery-powered sensor networks, focusing on the fixed-size and fixed-interval buffering schemes. The main motivation is to address the yet poorly understood size variation-induced effect on power-aware buffering schemes. Our theoretical analysis elucidates the fundamental differences between the fixed-size and fixed-interval buffering schemes in the presence of data size variation. It shows that data size variation has detrimental effects on the power expenditure of the fixed-size buffering in general, and reveals that the size variation induced effects can be either mitigated by a positive skewness or promoted by a negative skewness in size distribution. By contrast, the fixed-interval buffering scheme has an obvious advantage of being eminently immune to the data-size variation. Hence the fixed-interval buffering scheme is a risk-averse strategy for its robustness in a variety of operational environments. In addition, based on the fixed-interval buffering scheme, we establish the power consumption relationship between child nodes and parent node in a static data collection tree, and give an in-depth analysis of the impact of child bandwidth distribution on parent's power consumption. This study is of practical significance: it sheds new light on the relationship among power consumption of buffering schemes, power parameters of radio module and memory bank, data arrival rate and data size variation, thereby providing well-informed guidance in determining an optimal buffer size (interval) to maximize the operational lifespan of sensor networks.

cs.NI↗

arXiv2010

On Optimal Deadlock Detection Scheduling

Deadlock detection scheduling is an important, yet often overlooked problem that can significantly affect the overall performance of deadlock handling. Excessive initiation of deadlock detection increases overall message usage, resulting in degraded system performance in the absence of deadlocks; while insufficient initiation of deadlock detection increases the deadlock persistence time, resulting in an increased deadlock resolution cost in the presence of deadlocks. The investigation of this performance tradeoff, however, is missing in the literature. This paper studies the impact of deadlock detection scheduling on the overall performance of deadlock handling. In particular, we show that there exists an optimal deadlock detection frequency that yields the minimum long-run mean average cost, which is determined by the message complexities of the deadlock detection and resolution algorithms being used, as well as the rate of deadlock formation, denoted as $λ$. For the best known deadlock detection and resolution algorithms, we show that the asymptotically optimal frequency of deadlock detection scheduling that minimizes the overall message overhead is ${\cal O}((λn)^{1/3})$, when the total number $n$ of processes is sufficiently large. Furthermore, we show that in general fully distributed (uncoordinated) deadlock detection scheduling cannot be performed as efficiently as centralized (coordinated) deadlock detection scheduling.

cs.DC↗

arXiv2010

Control spiral wave dynamics using feedback signals from line detectors

We numerically study trajectories of spiral-wave-cores in excitable systems modulated proportionally to the integral of the activity on the straight line, several or dozens of equi-spaced measuring points on the straight line, the double-line and the contour-line. We show the single-line feedback results in the drift of core center along a straight line being parallel to the detector. An interesting finding is that the drift location in $y$ is a piecewise linear-increasing function of both the feedback line location and time delay. Similar trajectory occurs when replacing the feedback line with several or dozens of equi-spaced measuring points on the straight line. This allows to move the spiral core to the desired location along a chosen direction by measuring several or dozens of points. Under the double-line feedback, the shape of the tip trajectory representing the competition between the first and second feedback lines is determined by the distance of two lines. Various drift attractors in spiral wave controlled by square-shaped contour-line feedback are also investigated. A brief explanation is presented.

cond-mat.stat-mech↗

arXiv2005

Pulse-duration dependence of high-order harmonic generation with coherent superposition state

We make a systematic study of high-order harmonic generation (HHG) in a He$^+$-like model ion when the initial states are prepared as a coherent superposition of the ground state and an excited state. It is found that, according to the degree of the ionization of the excited state, the laser intensity can be divided into three regimes in which HHG spectra exhibit different characteristics. The pulse-duration dependence of the HHG spectra in these regimes is studied. We also demonstrate evident advantages of using coherent superposition state to obtain high conversion efficiency. The conversion efficiency can be increased further if ultrashort laser pulses are employed.

physics.atom-ph↗