Author name cluster

Jing Zhou

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.

14 papers

2 author rows

AAAI Conference 2026 Conference Paper

Benchmarking and Enhancing Rule Knowledge-Driven Reasoning of Large Language Models

Zijie Xu
Wenjun Ke
Peng Wang
Guozheng Li
Qingjian Ni
Jiajun Liu
Ziyu Shang
Jing Zhou

Large Language Models (LLMs) have demonstrated strong capabilities across diverse tasks under the example-driven learning paradigm. However, in high-stakes domains such as emergency response and industrial safety, historical incidents are scarce, confidential, or both, while concise rule books are abundant. We formalize this underexplored setting as rule knowledge-driven reasoning and ask: Can LLMs reason reliably when rules are plentiful but examples are nearly absent? To study this question, we introduce RULER, an automatic benchmark that generates 32K rigorously verified questions from 1K expert-curated emergency response rules to probe three core abilities: rule memorization, single-rule application, and multi-rule complex reasoning. RULER is further equipped with a hallucination-aware evaluation suite and novel relational metrics. A comprehensive empirical study of five representative LLMs and five enhancement strategies shows that, even when models achieve reliable performance on rule memorization and single-rule application, multi-rule complex reasoning plateaus at 5.4 on a 10-point scale. To address this limitation, we propose RAMPS, a Rule knowledge-Aware Monte Carlo Tree Search Process-reward Supervision framework. RAMPS injects rule knowledge priors into MCTS, distills 12K step-level traces without human annotation, and trains an advantage-based reward model that scores candidate reasoning paths during beam search inference. Experimental results show that RAMPS significantly improves multi-rule complex reasoning performance to 7.7.

PDF Details DOI

EAAI Journal 2025 Journal Article

A dynamic graph convolutional network-based framework for the unsteady operating states recognition of multi-product pipeline systems

Li Zhang
Lin Fan
Jianjun Liu
Dingyu Jiao
Yuxuan He
Jing Zhou
Karine Zeitouni
Huai Su

Considering that the existing methods lack spatial and temporal information mining of pipeline multidimensional operation data, it is unable to accurately recognize the unsteady operation conditions among pipeline stations. In this study, a dynamic graph convolutional network classification model is proposed for the recognition of unsteady operating states in multi-product pipeline systems. Firstly, dynamic graph convolutional network of multi-pipeline system (DPipeNet) is constructed based on the visibility graph algorithm, mutual information and long and short-term memory network model. Secondly, static graph convolutional network of multi-pipeline system (SPipeNet) is constructed by using the real geographic location information of each station of multi-pipeline. Then, the input subgraph of the graph convolutional network is used to construct the multi-pipeline system operational state relationship network (OSRN), and the vulnerable state nodes of the system are evaluated using complex network centrality metrics. Finally, the proposed model is applied to real operational data of a multi-pipeline system in China. The results show that in the two-classification scenario, both DPipeNet and SPipeNet have higher accuracies, but DPipeNet has a lower missed rate. In the multi-classification scenario, DPipeNet has the highest precision, which can reach more than 85%, and the recall rate is improved by 13%–25% compared with the neural network models in recent literature and SPipeNet. In the vulnerability analysis scenario, the intermediate station pump startup/stoppage of multi-pipeline has higher vulnerability. The proposed method also provides decision support for managers in pipeline system operation and maintenance management.

Details DOI

EAAI Journal 2025 Journal Article

Enhanced Cross-Dimensional Transformer for long-term wellhead pressure forecasting during hydraulic fracturing

Tao Zhang
Yuan Zhong
Jing Zhou
Ping Li
Jie Gong

Observational analysis of wellhead pressure variations is crucial for detecting fracturing fluid leakage and assessing wellbore integrity during fracturing operations. Accurately predicting multi-time step pressure changes is essential for enhancing oil and gas extraction efficiency while ensuring wellhead safety. This paper proposes the Enhanced Cross-Dimensional Transformer (ECformer), a time series model that predicts long-term wellhead pressure by capturing time-variable dependencies, the cross-dimensional information, in fracturing operation data. ECformer employs Patch Generation to segment local data regions, enabling the Cross-Dimensional Enhancement Structure to capture latent time-variable relationships. Patch Shuffle and Multi-Scale Fusion further refine temporal extraction and feature-level analysis at the patch scale, thereby enhancing prediction accuracy. Experimental results show that ECformer outperforms the newer Near Time Transformer (NTformer) and Patch Time Series Transformer (PatchTST) in long-term wellhead pressure prediction, reducing the Mean Squared Error (MSE) by 3. 5% and 33. 4% within 90 s and by 6. 6% and 38. 5% within 120 s about the average of multiple data sets. ECformer shows higher accuracy in long-step predictions, providing greater potential for future proactive risk prevention.

Details DOI

IROS Conference 2025 Conference Paper

Muscle-on-a-Chip: A Self-Healing Actuator Platform in Robotic Systems

Hongze Yin
Jing Zhou
Juan Zhang
Huiying Yang
Jiahao Wang
Yuyin Zhang
Yue Wang
Na Liu

The regulation of muscle function is very important for tissue engineering and sports science. This paper presents a simple microfluidic chip platform and its control method to investigate the regulation of muscle function. By employing C2C12 cells as the model system for skeletal muscle research, these cells were inoculated onto the microfluidic chips and induced to differentiate into fully functional muscle tubes. Programmable actuation control enables localized strain gradients within the microfluidic platform, achieving differential mechanical regimes for functional modulation of integrated muscle constructs. The system implements mechanical conditioning to recapitulate exercise-induced myocyte damage and subsequent regenerative processes through controlled deformation protocols. Our radial-strain actuators generate 19. 4% maximum principal strain, while axial-strain configurations achieve 8. 3% baseline deformation. Dynamic input modulation enables precise strain reduction to 7. 4% and 2. 2%, respectively establishing differential mechanical regimes for simulating exercise-associated functional impairment (high-strain phase) and recovery processes (low-strain phase). This strain-programmable platform establishes a robust framework for investigating mechanobiological thresholds in functional muscle regeneration.

Details

NeurIPS Conference 2025 Conference Paper

PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization

Yiming Huang
Yajie Hao
Yuxuan Du
Jing Zhou
Xiao Yuan
Xiaoting Wang

Variational Quantum Algorithms (VQAs) are emerging as leading strategies with the potential to unlock practical applications and deliver significant advantages in the investigation of many-body quantum systems and quantum chemistry. A key challenge hindering the application of VQAs to large-scale problems is rooted in the no-cloning theorem in quantum mechanics, precluding standard backpropagation and leading to prohibitive quantum resource expenditure such as measurement cost. To address this challenge, we reformulate the training dynamics of VQAs as a non-linear partial differential equation and propose a novel protocol that leverages physics-informed neural networks (PINNs) to model this dynamical system efficiently. Given a small amount of training trajectory data collected from quantum devices, our protocol predicts the parameter updates of VQAs over multiple iterations on the classical side, dramatically reducing quantum resource costs. Through systematic numerical experiments, we demonstrate that our method achieves up to a 30x speedup compared to conventional methods and reduces quantum resource costs by as much as 90\% for tasks involving up to 40 qubits, including ground state preparation of different quantum systems, while maintaining competitive accuracy. Our approach complements existing techniques aimed at improving the efficiency of VQAs and further strengthens their potential for practical applications.

PDF Details

YNIMG Journal 2025 Journal Article

The brain-gut microbiota network (BGMN) is correlated with symptom severity and neurocognition in patients with schizophrenia

Runlin Peng
Wei Wang
Liqin Liang
Rui Han
Yi Li
Haiyuan Wang
Yuran Wang
Wenhao Li

The association between the human brain and gut microbiota, known as the "brain-gut-microbiota axis", is involved in the neuropathological mechanisms of schizophrenia (SZ); however, its association patterns and correlations with symptom severity and neurocognition are still largely unknown. In this study, 43 SZ patients and 55 normal controls (NCs) were included, and resting-state functional magnetic resonance imaging (rs-fMRI) and gut microbiota data were acquired for each participant. First, the brain features of brain images and functional brain networks were computed from rs-fMRI data; the gut features of gut microbiota abundance and the gut microbiota network were computed from gut microbiota data. Second, we propose a novel methodology to construct an individual brain-gut microbiota network (BGMN) for each participant by combining the brain and gut features via multiple strategies. Third, discriminative models between SZ patients and NCs were built using the connectivity matrices of the BGMN as input features. Moreover, the correlations between the most discriminative features and the scores of symptom severity and neurocognition were analyzed in SZ patients. The results showed that the best discriminative model between SZ patients and NCs was achieved using the connectivity matrices of the BGMN when all the brain and gut features were integrated, with an accuracy of 0.90 and an area under the curve value of 0.97. The most discriminative features were related primarily to the genera Faecalibacterium and Collinsella, in which the genus Faecalibacterium was linked to the visual system and subcortical cortices and the genus Collinsella was linked to the default network and subcortical cortices. Furthermore, parts of the most discriminative features were significantly correlated with the scores of neurocognition in the SZ patients. The methodology for constructing individual BGMNs proposed in this study can help us reveal the associations between the brain and gut microbiota and understand the neuropathology of SZ.

Details DOI

JMLR Journal 2024 Journal Article

Gaussian Mixture Models with Rare Events

Xuetong Li
Jing Zhou
Hansheng Wang

We study here a Gaussian mixture model (GMM) with rare events data. In this case, the commonly used Expectation-Maximization (EM) algorithm exhibits extremely slow numerical convergence rate. To theoretically understand this phenomenon, we formulate the numerical convergence problem of the EM algorithm with rare events data as a problem about a contraction operator. Theoretical analysis reveals that the spectral radius of the contraction operator in this case could be arbitrarily close to 1 asymptotically. This theoretical finding explains the empirical slow numerical convergence of the EM algorithm with rare events data. To overcome this challenge, a Mixed EM (MEM) algorithm is developed, which utilizes the information provided by partially labeled data. As compared with the standard EM algorithm, the key feature of the MEM algorithm is that it requires additionally labeled data. We find that MEM algorithm significantly improves the numerical convergence rate as compared with the standard EM algorithm. The finite sample performance of the proposed method is illustrated by both simulation studies and a real-world dataset of Swedish traffic signs. [abs] [ pdf ][ bib ] &copy JMLR 2024. ( edit, beta )

PDF Details

YNICL Journal 2024 Journal Article

Relationships among the gut microbiome, brain networks, and symptom severity in schizophrenia patients: A mediation analysis

Liqin Liang
Shijia Li
Yuanyuan Huang
Jing Zhou
Dongsheng Xiong
Shaochuan Li
Hehua Li
Baoyuan Zhu

The microbiome-gut-brain axis (MGBA) plays a critical role in schizophrenia (SZ). However, the underlying mechanisms of the interactions among the gut microbiome, brain networks, and symptom severity in SZ patients remain largely unknown. Fecal samples, structural and functional magnetic resonance imaging (MRI) data, and Positive and Negative Syndrome Scale (PANSS) scores were collected from 38 SZ patients and 38 normal controls, respectively. The data of 16S rRNA gene sequencing were used to analyze the abundance of gut microbiome and the analysis of human brain networks was applied to compute the nodal properties of 90 brain regions. A total of 1,691,280 mediation models were constructed based on 261 gut bacterial, 810 nodal properties, and 4 PANSS scores in SZ patients. A strong correlation between the gut microbiome and brain networks (r = 0.89, false discovery rate (FDR) -corrected p < 0.05) was identified. Importantly, the PANSS scores were linearly correlated with both the gut microbiome (r = 0.5, FDR-corrected p < 0.05) and brain networks (r = 0.59, FDR-corrected p < 0.05). The abundance of genus Sellimonas significantly affected the PANSS negative scores of SZ patients via the betweenness centrality of white matter networks in the inferior frontal gyrus and amygdala. Moreover, 19 significant mediation models demonstrated that the nodal properties of 7 brain regions, predominately from the systems of visual, language, and control of action, showed significant mediating effects on the PANSS scores with the gut microbiome as mediators. Together, our findings indicated the tripartite relationships among the gut microbiome, brain networks, and PANSS scores and suggested their potential role in the neuropathology of SZ.

Details DOI

ICLR Conference 2023 Conference Paper

Not All Tasks Are Born Equal: Understanding Zero-Shot Generalization

Jing Zhou
Zongyu Lin
Yanan Zheng
Jian Li 0015
Zhilin Yang 0001

Recent work has achieved remarkable zero-shot performance with multi-task prompted pretraining, but little has been understood. For the first time, we show that training on a small number of key tasks beats using all the training tasks, while removing these key tasks substantially hurts performance. We also find that these key tasks are mostly question answering (QA) tasks. These novel findings combined deepen our understanding about zero-shot generalization—training on certain tasks such as QA encodes general knowledge transferable to a wide range of tasks. In addition, to automate this procedure, we devise a method that (1) identifies key training tasks without observing the test tasks by examining the pairwise generalization results and (2) resamples training tasks for better data distribution. Empirically, our approach achieves improved results across various model scales and tasks.

Details

IJCAI Conference 2022 Conference Paper

A Universal PINNs Method for Solving Partial Differential Equations with a Point Source

Xiang Huang
Hongsheng Liu
Beiji Shi
Zidong Wang
Kang Yang
Yang Li
Min Wang
Haotian Chu

In recent years, deep learning technology has been used to solve partial differential equations (PDEs), among which the physics-informed neural networks (PINNs)method emerges to be a promising method for solving both forward and inverse PDE problems. PDEs with a point source that is expressed as a Dirac delta function in the governing equations are mathematical models of many physical processes. However, they cannot be solved directly by conventional PINNs method due to the singularity brought by the Dirac delta function. In this paper, we propose a universal solution to tackle this problem by proposing three novel techniques. Firstly the Dirac delta function is modeled as a continuous probability density function to eliminate the singularity at the point source; secondly a lower bound constrained uncertainty weighting algorithm is proposed to balance the physics-informed loss terms of point source area and the remaining areas; and thirdly a multi-scale deep neural network with periodic activation function is used to improve the accuracy and convergence speed. We evaluate the proposed method with three representative PDEs, and the experimental results show that our method outperforms existing deep learning based methods with respect to the accuracy, the efficiency and the versatility.

PDF Details DOI

ICML Conference 2020 Conference Paper

Rate-distortion optimization guided autoencoder for isometric embedding in Euclidean latent space

Keizo Kato
Jing Zhou
Tomotake Sasaki
Akira Nakagawa

To analyze high-dimensional and complex data in the real world, deep generative models, such as variational autoencoder (VAE) embed data in a low-dimensional space (latent space) and learn a probabilistic model in the latent space. However, they struggle to accurately reproduce the probability distribution function (PDF) in the input space from that in the latent space. If the embedding were isometric, this issue can be solved, because the relation of PDFs can become tractable. To achieve isometric property, we propose Rate-Distortion Optimization guided autoencoder inspired by orthonormal transform coding. We show our method has the following properties: (i) the Jacobian matrix between the input space and a Euclidean latent space forms a constantly-scaled orthonormal system and enables isometric data embedding; (ii) the relation of PDFs in both spaces can become tractable one such as proportional relation. Furthermore, our method outperforms state-of-the-art methods in unsupervised anomaly detection with four public datasets.

Details

EAAI Journal 2019 Journal Article

Improving the effectiveness of keyword search in databases using query logs

Ziqiang Yu
Ajith Abraham
Xiaohui Yu
Yang Liu
Jing Zhou
Kun Ma

Using query logs to enhance user experience has been extensively studied in the Web IR literature. However, in the area of keyword search on structured data (relational databases in particular), most existing works have focused on improving search result quality via designing better scoring functions, without giving explicit consideration to query logs. However, query logs can reflect the user preferences, so our work taps into the wealth of information contained in query logs and aims to enhance the search effectiveness by explicitly taking into account the log information when ranking the query results. Different from existing approaches only relying on a schema graph or a data graph, our work designs a comprehensive solution based on both the schema graph and the data graph for discovering top-k results with two stages. First, we identify top-k candidate networks with a query-log-aware ranking strategy by employing the largest frequent subtrees mined from query logs. Since a candidate network usually corresponds to multiple joined tuple trees, we further rank these joined tuple trees with the PageRank principle based on the data graph in the second stage. Finally, user studies on a real dataset validate the effectiveness of the proposed ranking strategy.

Details DOI

EAAI Journal 2016 Journal Article

Automatic bearing fault diagnosis using particle swarm clustering and Hidden Markov Model

Mitchell Yuwono
Yong Qin
Jing Zhou
Ying Guo
Branko G. Celler
Steven W. Su

Ball bearings are integral elements in most rotating manufacturing machineries. While detecting defective bearing is relatively straightforward, discovering the source of defect requires advanced signal processing techniques. This paper proposes an automatic bearing defect diagnosis method based on Swarm Rapid Centroid Estimation (SRCE) and Hidden Markov Model (HMM). Using the defect frequency signatures extracted with Wavelet Kurtogram and Cepstral Liftering, SRCE+HMM achieved on average the sensitivity, specificity, and error rate of 98. 02%, 96. 03%, and 2. 65%, respectively, on the bearing fault vibration data provided by Case School of Engineering of the Case Western Reserve University (CSE) which warrants further investigation.

Details DOI

JMLR Journal 2006 Journal Article

Streamwise Feature Selection

Jing Zhou
Dean P. Foster
Robert A. Stine
Lyle H. Ungar

In streamwise feature selection, new features are sequentially considered for addition to a predictive model. When the space of potential features is large, streamwise feature selection offers many advantages over traditional feature selection methods, which assume that all features are known in advance. Features can be generated dynamically, focusing the search for new features on promising subspaces, and overfitting can be controlled by dynamically adjusting the threshold for adding features to the model. In contrast to traditional forward feature selection algorithms such as stepwise regression in which at each step all possible features are evaluated and the best one is selected, streamwise feature selection only evaluates each feature once when it is generated. We describe information-investing and α-investing, two adaptive complexity penalty methods for streamwise feature selection which dynamically adjust the threshold on the error reduction required for adding a new feature. These two methods give false discovery rate style guarantees against overfitting. They differ from standard penalty methods such as AIC, BIC and RIC, which always drastically over- or under-fit in the limit of infinite numbers of non-predictive features. Empirical results show that streamwise regression is competitive with (on small data sets) and superior to (on large data sets) much more compute-intensive feature selection methods such as stepwise regression, and allows feature selection on problems with millions of potential features. [abs] [ pdf ][ bib ] &copy JMLR 2006. ( edit, beta )

PDF Details