Author name cluster

Shaoyu Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

AAAI Conference 2026 Conference Paper

Incremental Maintenance of DatalogMTL Materialisations

Kaiyue Zhao
Dingqi Chen
Shaoyu Wang
Pan Hu

DatalogMTL extends the classical Datalog language with metric temporal logic (MTL), enabling expressive reasoning over temporal data. While existing reasoning approaches, such as materialisation-based and automata-based methods, offer soundness and completeness, they lack support for handling efficient dynamic updates—a crucial requirement for real-world applications that involve frequent data updates. In this work, we propose DRedMTL, an incremental reasoning algorithm for DatalogMTL with bounded intervals. Our algorithm builds upon the classical Delete/Rederive (DRed) algorithm, which incrementally updates the materialisation of a Datalog program. Unlike a Datalog materialisation which is in essence a finite set of facts, a DatalogMTL materialisation has to be represented as a finite set of facts plus periodic intervals indicating how the full materialisation can be constructed through unfolding. To cope with this, our algorithm is equipped with specifically designed operators to efficiently handle such periodic representations of DatalogMTL materialisations. We have implemented this approach and tested it on several publicly available datasets. Experimental results show that DRedMTL often significantly outperforms rematerialisation, sometimes by orders of magnitude.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Goal-Driven Reasoning in DatalogMTL with Magic Sets

Shaoyu Wang
Kaiyue Zhao
Dongliang Wei
Przemysław Andrzej Wałęga
Dingmin Wang
Hongming Cai
Pan Hu

DatalogMTL is a powerful rule-based language for temporal reasoning. Due to its high expressive power and flexible modeling capabilities, it is suitable for a wide range of applications, including tasks from industrial and financial sectors. However, due its high computational complexity, practical reasoning in DatalogMTL is highly challenging. To address this difficulty, we introduce a new reasoning method for DatalogMTL which exploits the magic sets technique—a rewriting approach developed for (non-temporal) Datalog to simulate top-down evaluation with bottom-up reasoning. We have implemented this approach and evaluated it on publicly available benchmarks, showing that the proposed approach significantly and consistently outperformed state-of-the-art reasoning techniques.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training

Ziming Liu
Shaoyu Wang
Shenggan Cheng
Zhongkai Zhao
Kai Wang
Xuanlei Zhao
James Demmel
Yang You

Training Transformer models on long sequences in a distributed setting poses significant challenges in terms of efficiency and scalability. Current methods are either constrained by the number of attention heads or excessive communication overheads. To address this problem, we propose StarTrail, a multi-dimensional concentric distributed training system for long sequences, fostering an efficient communication paradigm and providing additional tuning flexibility for communication arrangements. Specifically, StarTrail introduces an extra parallel dimension and divides the peer-to-peer communication into sub-rings to substantially reduce communication volume and avoid bandwidth bottlenecks. Through comprehensive experiments across diverse hardware environments and on both Natural Language Processing (NLP) and Computer Vision (CV) tasks, we demonstrate that our approach significantly surpasses state-of-the-art methods that support Long sequence lengths, achieving performance improvements of up to 77. 12% on GPT-style models and up to 114. 33% on DiT (Diffusion Transformer) models without affecting the computations results.

PDF Details

JBHI Journal 2025 Journal Article

Virtual-mask Informed Prior for Sparse-view Dual-Energy CT Reconstruction

Zini Chen
Yao Xiao
Junyan Zhang
Mohan Li
Cunfeng Wei
Shaoyu Wang
Liu Shi
Qiegen Liu

Sparse-view sampling in dual-energy computed tomography (DECT) significantly reduces radiation dose and increases imaging speed, yet is highly prone to artifacts. Although diffusion models have demonstrated potential in effectively handling incomplete data, most existing methods in this field focus on the image domain and lack global constraints, which consequently leads to insufficient reconstruction quality. In this study, we propose a dual-domain virtual-mask informed diffusion model for sparse-view reconstruction by leveraging the high inter-channel correlation in DECT. Specifically, the study designs a virtual mask and applies it to the high-energy and low-energy data to perform perturbation operations, thus constructing high-dimensional tensors that serve as the prior information of the diffusion model. In addition, a dual-domain collaboration strategy is adopted to integrate the information of the randomly selected high-frequency components in the wavelet domain with the information in the projection domain, for the purpose of optimizing the global structures and local details. The experimental results show that the method exhibits excellent performance on multiple datasets. Under 30-view sparse sampling conditions, VIP-DECT improves PSNR by at least 1. 02 dB and enhances SSIM by 1. 91%.

Details DOI

AAAI Conference 2023 Conference Paper

Anomaly Segmentation for High-Resolution Remote Sensing Images Based on Pixel Descriptors

Jingtao Li
Xinyu Wang
Hengwei Zhao
Shaoyu Wang
Yanfei Zhong

Anomaly segmentation in high spatial resolution (HSR) remote sensing imagery is aimed at segmenting anomaly patterns of the earth deviating from normal patterns, which plays an important role in various Earth vision applications. However, it is a challenging task due to the complex distribution and the irregular shapes of objects, and the lack of abnormal samples. To tackle these problems, an anomaly segmentation model based on pixel descriptors (ASD) is proposed for anomaly segmentation in HSR imagery. Specifically, deep one-class classification is introduced for anomaly segmentation in the feature space with discriminative pixel descriptors. The ASD model incorporates the data argument for generating virtual abnormal samples, which can force the pixel descriptors to be compact for normal data and meanwhile to be diverse to avoid the model collapse problems when only positive samples participated in the training. In addition, the ASD introduced a multi-level and multi-scale feature extraction strategy for learning the low-level and semantic information to make the pixel descriptors feature-rich. The proposed ASD model was validated using four HSR datasets and compared with the recent state-of-the-art models, showing its potential value in Earth vision applications.

PDF Details DOI

TCS Journal 2016 Journal Article

Molecular computers for molecular robots as hybrid systems

Masami Hagiya
Nathanael Aubert-Kato
Shaoyu Wang
Satoshi Kobayashi

Various artificial molecular devices, including some made of DNA or RNA, have been developed to date. The next step in this area of research is to develop an integrated system from such molecular devices. A molecular robot consists of sensors, computers, and actuators, all made of molecular devices, and reacts autonomously to its environment by observing the environment, making decisions with its computers, and performing actions upon the environment. Molecular computers should thus be the intelligent controllers of such molecular robots. Such controllers can naturally be regarded as hybrid systems because the environment, the robot, and the controller are all state transition systems having discrete and continuous states and transitions. For modeling and designing hybrid systems, formal frameworks, such as hybrid automata, are commonly used. In this perspective paper, we examine how molecular controllers can be modeled as hybrid automata and how they can be realized in a molecular robot. We first summarize the requirements for such molecular controllers and examine existing frameworks of DNA computing with respect to these requirements. We then show the possibility of combining existing frameworks of DNA computing to implement a sample hybrid controller for a molecular robot.

Details DOI