SZShandian Zhe

Shandian Zhe

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shandian Zhe has a total of 85 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Streaming Sparse Cholesky Method for Derivative-Informed Gaussian Process Surrogates Within Digital Twin Applications

    by Shridhar Vashishtha, Krishna Prasath Logakannan, Jacob Hochhalter, Shandian Zhe, Robert M. Kirby

  • Efficiently training SciML models with derivative-informed training data using order truncated imaginary numbers

    by Krishna Prasath Logakannan, Mauricio Aristizabal, Geoffrey Bomarito, Zhitong Xu, Shandian Zhe, Robert M. Kirby, Harry Millwater, Jacob Hochhalter


  • Top Cited Papers
    Open Access

    The Development and Use of AI Chatbots for Health Behavior Change: Scoping Review

    by Lingyi Fu, Ryan Burns, Yuhuan Xie, Jincheng Shen, Shandian Zhe, Paul Estabrooks, Yang Bai

    Background: Artificial intelligence (AI) chatbots are technologies that facilitate human-computer interaction through communication in a natural language format. By increasing cost-effectiveness, interaction, autonomy, personalization, and support, mobile health interventions can benefit health behavior change and make it more natural and intuitive. Objective: This study aimed to provide an up-to-date and practical overview of how text-based AI chatbots are designed, developed, and evaluated across 8 health behaviors, including their roles, theoretical foundations, health behavior change techniques, technology development workflow, and performance validation framework. Methods: In accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) framework, relevant studies published before March 2024 were identified from 9 bibliographic databases (ie, PubMed, CINAHL, MEDLINE, Embase, Web of Science, Scopus, APA PsycINFO, IEEE Xplore, and ACM Digital Library). Two stages (ie, title and abstract screening followed by full-text screening) were conducted to screen the eligibility of the papers via Covidence software. Finally, we extracted the data via Microsoft Excel software and used a narrative approach, content analysis, and evidence map to synthesize the reported results. Results: Our systematic search initially identified 10,508 publications, 43 of which met our inclusion criteria. AI chatbots primarily served 2 main roles: routine coach (27/43, 62.79%) and on-demand assistant (12/43, 27.91%), while 4 studies (4/43, 9.30%) integrated both roles. Frameworks like cognitive behavioral therapy (13/24, 54.17%) and behavior change techniques, such as goal setting, feedback and monitoring, and social support, guided the development of theory-driven AI chatbots. Noncode platforms (eg, Google Dialogflow and IBM Watson) integrated with social messaging platforms (eg, Facebook Messenger) were commonly used to develop AI chatbots (23/43, 53.49%). AI chatbots have been evaluated across 4 domains: technical performance (17/43, 39.53%), usability (17/43, 39.53%), engagement (37/43, 86.05%), and health behavior change (33/43, 76.74%). Evidence for health behavior changes remains exploratory but promising. Among 33 studies with 120 comparisons, 81.67% (98/120) showed positive outcomes, though only 35.83% (43/120) had moderate or larger effects (Hedges g or odds ratio or Cohen d>0.5). Most involved nonclinical (36/43, 83.72%) and adults (23/43, 53.49%), and a few were randomized controlled trials (14/43, 32.56%). Benefits were mainly seen in physical activity, smoking cessation, stress management, and diet, with limited evidence for other behaviors. Findings were inconsistent regarding the influence of long-term effects, intervention duration, modality, and engagement on health behavior change outcomes. Conclusions: The exploratory synthesis provides a roadmap for developing and evaluating AI chatbots in health behavior change, highlighting the need for further research on cost, implementation outcomes, and underexplored behaviors such as sleep, weight management, sedentary behavior, and alcohol use.


  • Open Access

    Semantics-Driven 3D Scene Retrieval via Joint Loss Deep Learning

    by Juefei Yuan, Tianyang Wang, Shandian Zhe, Yijuan Lu, Zhaoxian Zhou, Bo Li

    Three-dimensional (3D) scene model retrieval has emerged as a novel and challenging area within content-based 3D model retrieval research. It plays an increasingly critical role in various domains, such as video games, film production, and immersive technologies, including virtual reality (VR), augmented reality (AR), and mixed reality (MR), where automated generation of 3D content is highly desirable. Despite their potential, the existing 3D scene retrieval techniques often overlook the rich semantic relationships among objects and between objects and their surrounding scenes. To address this gap, we introduce a comprehensive scene semantic tree that systematically encodes learned object occurrence probabilities within each scene category, capturing essential semantic information. Building upon this structure, we propose a novel semantics-driven image-based 3D scene retrieval method. The experimental evaluations show that the proposed approach effectively models scene semantics, enables more accurate similarity assessments between 3D scenes, and achieves substantial performance improvements. All the experimental results, along with the associated code and datasets, are available on the project website.


  • Open Access

    Multi-Operator Few-Shot Learning for Generalization Across PDE Families

    by Yile Li, Shandian Zhe

    Learning solution operators for partial differential equations (PDEs) has become a foundational task in scientific machine learning. However, existing neural operator methods require abundant training data for each specific PDE and lack the ability to generalize across PDE families. In this work, we propose MOFS: a unified multimodal framework for multi-operator few-shot learning, which aims to generalize to unseen PDE operators using only a few demonstration examples. Our method integrates three key components: (i) multi-task self-supervised pretraining of a shared Fourier Neural Operator (FNO) encoder to reconstruct masked spatial fields and predict frequency spectra, (ii) text-conditioned operator embeddings derived from statistical summaries of input-output fields, and (iii) memory-augmented multimodal prompting with gated fusion and cross-modal gradient-based attention. We adopt a two-stage training paradigm that first learns prompt-conditioned inference on seen operators and then applies end-to-end contrastive fine-tuning to align latent representations across vision, frequency, and text modalities. Experiments on PDE benchmarks, including Darcy Flow and Navier Stokes variants, demonstrate that our model outperforms existing operator learning baselines in few-shot generalization. Extensive ablations validate the contributions of each modality and training component. Our approach offers a new foundation for universal and data-efficient operator learning across scientific domains.

  • Open Access

    The Development and Use of AI Chatbots for Health Behavior Change: Scoping Review (Preprint)

    by Lingyi Fu, Ryan Burns, Yuhuan Xie, Jincheng Shen, Shandian Zhe, Paul Estabrooks, Yang Bai

    BACKGROUND Artificial intelligence (AI) chatbots are technologies that facilitate human-computer interaction through communication in a natural language format. By increasing cost-effectiveness, interaction, autonomy, personalization, and support, mobile health interventions can benefit health behavior change and make it more natural and intuitive. OBJECTIVE This study aimed to provide an up-to-date and practical overview of how text-based AI chatbots are designed, developed, and evaluated across 8 health behaviors, including their roles, theoretical foundations, health behavior change techniques, technology development workflow, and performance validation framework. METHODS In accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) framework, relevant studies published before March 2024 were identified from 9 bibliographic databases (ie, PubMed, CINAHL, MEDLINE, Embase, Web of Science, Scopus, APA PsycINFO, IEEE Xplore, and ACM Digital Library). Two stages (ie, title and abstract screening followed by full-text screening) were conducted to screen the eligibility of the papers via Covidence software. Finally, we extracted the data via Microsoft Excel software and used a narrative approach, content analysis, and evidence map to synthesize the reported results. RESULTS Our systematic search initially identified 10,508 publications, 43 of which met our inclusion criteria. AI chatbots primarily served 2 main roles: routine coach (27/43, 62.79%) and on-demand assistant (12/43, 27.91%), while 4 studies (4/43, 9.30%) integrated both roles. Frameworks like cognitive behavioral therapy (13/24, 54.17%) and behavior change techniques, such as goal setting, feedback and monitoring, and social support, guided the development of theory-driven AI chatbots. Noncode platforms (eg, Google Dialogflow and IBM Watson) integrated with social messaging platforms (eg, Facebook Messenger) were commonly used to develop AI chatbots (23/43, 53.49%). AI chatbots have been evaluated across 4 domains: technical performance (17/43, 39.53%), usability (17/43, 39.53%), engagement (37/43, 86.05%), and health behavior change (33/43, 76.74%). Evidence for health behavior changes remains exploratory but promising. Among 33 studies with 120 comparisons, 81.67% (98/120) showed positive outcomes, though only 35.83% (43/120) had moderate or larger effects (Hedges g or odds ratio or Cohen d>0.5). Most involved nonclinical (36/43, 83.72%) and adults (23/43, 53.49%), and a few were randomized controlled trials (14/43, 32.56%). Benefits were mainly seen in physical activity, smoking cessation, stress management, and diet, with limited evidence for other behaviors. Findings were inconsistent regarding the influence of long-term effects, intervention duration, modality, and engagement on health behavior change outcomes. CONCLUSIONS The exploratory synthesis provides a roadmap for developing and evaluating AI chatbots in health behavior change, highlighting the need for further research on cost, implementation outcomes, and underexplored behaviors such as sleep, weight management, sedentary behavior, and alcohol use.

  • Open Access

    Diffusion-Based Symbolic Regression

    by Zachary Bastiani, Robert M. Kirby, Jacob Hochhalter, Shandian Zhe

    Diffusion has emerged as a powerful framework for generative modeling, achieving remarkable success in applications such as image and audio synthesis. Enlightened by this progress, we propose a novel diffusion-based approach for symbolic regression. We construct a random mask-based diffusion and denoising process to generate diverse and high-quality equations. We integrate this generative processes with a token-wise Group Relative Policy Optimization (GRPO) method to conduct efficient reinforcement learning on the given measurement dataset. In addition, we introduce a long short-term risk-seeking policy to expand the pool of top-performing candidates, further enhancing performance. Extensive experiments and ablation studies have demonstrated the effectiveness of our approach.

  • Open Access

    Graph-Based Operator Learning from Limited Data on Irregular Domains

    by Yile Li, Shandian Zhe

    Operator learning seeks to approximate mappings from input functions to output solutions, particularly in the context of partial differential equations (PDEs). While recent advances such as DeepONet and Fourier Neural Operator (FNO) have demonstrated strong performance, they often rely on regular grid discretizations, limiting their applicability to complex or irregular domains. In this work, we propose a Graph-based Operator Learning with Attention (GOLA) framework that addresses this limitation by constructing graphs from irregularly sampled spatial points and leveraging attention-enhanced Graph Neural Netwoks (GNNs) to model spatial dependencies with global information. To improve the expressive capacity, we introduce a Fourier-based encoder that projects input functions into a frequency space using learnable complex coefficients, allowing for flexible embeddings even with sparse or nonuniform samples. We evaluated our approach across a range of 2D PDEs, including Darcy Flow, Advection, Eikonal, and Nonlinear Diffusion, under varying sampling densities. Our method consistently outperforms baselines, particularly in data-scarce regimes, demonstrating strong generalization and efficiency on irregular domains.

  • Open Access

    Benchmarking Knowledge and Capability of Large Language Models in Building Science Domain

    by Gang Jiang, Keyan Chen, Jiatao Liu, Jianli Chen, Shandian Zhe, Zhe Wang

    Large language models (LLMs) are increasingly adopted across scientific and engineering fields. However, applying general-purpose LLMs to specialized engineering domains imposes stringent requirements for structured knowledge, rigorous reasoning, and technical precision. Thus, the suitability of current general-purpose LLMs for practical applications in engineering domains remains questionable. To understand the mastery level of LLMs in the building science domain as one broad but specific engineering domain, in this paper, we perform a comprehensive benchmark analysis (with benchmark dataset of 1,487 questions) to evaluate abilities of 15 state-of-the-art (SOTA) LLMs across 12 core subject topics in the building science domain. To enable scalable and robust evaluation, we propose and validate an AI-Judger for assessment across five dimensions of abilities, i.e., knowledge and concept, logic and consistency, clarity of expression, and reflection and exploratory. Overall, SOTA general-purposes LLMs achieve only ~50% accuracy on average in answering different types of questions. The capabilities of LLMs decrease progressively from linguistic expression and factual knowledge to logical reasoning, then reflection and exploratory thinking. For different tasks, LLMs exhibit notably low accuracy on calculation (~13%), short-answer (~23%), and cloze tasks (~30%), contrast to stronger performance on single-choice (74%) and multiple-choice questions (63%). Finally, pronounced variance of LLM performance exists across topics, with relatively low accuracy on physics fundamental and HVAC&R-related questions (median of 20%-40%) compared to ~80% for building standards and codes. These identified gaps highlight the limitations of general-purpose LLMs in engineering contexts, clearly pointing to the necessity of developing domain-specific LLMs tailored for engineering applications.


  • Open Access

    Multi-Resolution Active Learning of Fourier Neural Operators

    by Shibo Li, Xin Yu, Wei Xing, Mike Kirby, Akil Narayan, Shandian Zhe

    Fourier Neural Operator (FNO) is a popular operator learning framework. It not only achieves the state-of-the-art performance in many tasks, but also is efficient in training and prediction. However, collecting training data for the FNO can be a costly bottleneck in practice, because it often demands expensive physical simulations. To overcome this problem, we propose Multi-Resolution Active learning of FNO (MRA-FNO), which can dynamically select the input functions and resolutions to lower the data cost as much as possible while optimizing the learning efficiency. Specifically, we propose a probabilistic multi-resolution FNO and use ensemble Monte-Carlo to develop an effective posterior inference algorithm. To conduct active learning, we maximize a utility-cost ratio as the acquisition function to acquire new examples and resolutions at each step. We use moment matching and the matrix determinant lemma to enable tractable, efficient utility computation. Furthermore, we develop a cost annealing framework to avoid over-penalizing high-resolution queries at the early stage. The over-penalization is severe when the cost difference is significant between the resolutions, which renders active learning often stuck at low-resolution queries and inferior performance. Our method overcomes this problem and applies to general multi-fidelity active learning and optimization problems. We have shown the advantage of our method in several benchmark operator learning tasks. The code is available at https://github.com/shib0li/MRA-FNO.