Showing 1–27 of 27 results for author: Wan, N

MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering

Authors: Rezarta Islamaj, Robert Leaman, Joey Chan, Nicholas Wan, Qiao Jin, Natalie Xie, John Wilbur, Shubo Tian, Lana Yeganova, Po-Ting Lai, Chih-Hsuan Wei, Yifan Yang, Yao Ge, Qingqing Zhu, Zhizheng Wang, Zhiyong Lu

Abstract: Evaluating large language models (LLMs) in the biomedical domain requires benchmarks that can distinguish reasoning from pattern matching and remain discriminative as model capabilities improve. Existing biomedical question answering (QA) benchmarks are limited in this respect. Multiple-choice formats can allow models to succeed through answer elimination rather than inference, while widely circul… ▽ More Evaluating large language models (LLMs) in the biomedical domain requires benchmarks that can distinguish reasoning from pattern matching and remain discriminative as model capabilities improve. Existing biomedical question answering (QA) benchmarks are limited in this respect. Multiple-choice formats can allow models to succeed through answer elimination rather than inference, while widely circulated exam-style datasets are increasingly vulnerable to performance saturation and training data contamination. Multi-hop reasoning, defined as the ability to integrate information across multiple sources to derive an answer, is central to clinically meaningful tasks such as diagnostic support, literature-based discovery, and hypothesis generation, yet remains underrepresented in current biomedical QA benchmarks. MedHopQA is a disease-centered multi-hop reasoning benchmark consisting of 1,000 expert-curated question-answer pairs introduced as a shared task at BioCreative IX. Each question requires synthesis of information across two distinct Wikipedia articles, and answers are provided in an open-ended free-text format. Gold annotations are augmented with ontology-grounded synonym sets from MONDO, NCBI Gene, and NCBI Taxonomy to support both lexical and concept-level evaluation. MedHopQA was constructed through a structured process combining human annotation, triage, iterative verification, and LLM-as-a-judge validation. To reduce leaderboard gaming and contamination risk, the 1,000 scored questions are embedded within a publicly downloadable set of 10,000 questions, with answers withheld, on a CodaBench leaderboard. MedHopQA provides both a benchmark and a reusable framework for constructing future biomedical QA datasets that prioritize compositional reasoning, saturation resistance, and contamination resistance as core design constraints. △ Less

Submitted 12 May, 2026; originally announced May 2026.

DeepER-Med: Advancing Deep Evidence-Based Research in Medicine Through Agentic AI

Authors: Zhizheng Wang, Chih-Hsuan Wei, Joey Chan, Robert Leaman, Chi-Ping Day, Chuan Wu, Mark A Knepper, Antolin Serrano Farias, Jordina Rincon-Torroella, Hasan Slika, Betty Tyler, Ryan Huu-Tuan Nguyen, Asmita Indurkar, Mélanie Hébert, Shubo Tian, Lauren He, Noor Naffakh, Aseem Aseem, Nicholas Wan, Emily Y Chew, Tiarnan D L Keenan, Zhiyong Lu

Abstract: Trustworthiness and transparency are essential for the clinical adoption of artificial intelligence (AI) in healthcare and biomedical research. Recent deep research systems aim to accelerate evidence-grounded scientific discovery by integrating AI agents with multi-hop information retrieval, reasoning, and synthesis. However, most existing systems lack explicit and inspectable criteria for evidenc… ▽ More Trustworthiness and transparency are essential for the clinical adoption of artificial intelligence (AI) in healthcare and biomedical research. Recent deep research systems aim to accelerate evidence-grounded scientific discovery by integrating AI agents with multi-hop information retrieval, reasoning, and synthesis. However, most existing systems lack explicit and inspectable criteria for evidence appraisal, creating a risk of compounding errors and making it difficult for researchers and clinicians to assess the reliability of their outputs. In parallel, current benchmarking approaches rarely evaluate performance on complex, real-world medical questions. Here, we introduce DeepER-Med, a Deep Evidence-based Research framework for Medicine with an agentic AI system. DeepER-Med frames deep medical research as an explicit and inspectable workflow of evidence-based generation, consisting of three modules: research planning, agentic collaboration, and evidence synthesis. To support realistic evaluation, we also present DeepER-MedQA, an evidence-grounded dataset comprising 100 expert-level research questions derived from authentic medical research scenarios and curated by a multidisciplinary panel of 11 biomedical experts. Expert manual evaluation demonstrates that DeepER-Med consistently outperforms widely used production-grade platforms across multiple criteria, including the generation of novel scientific insights. We further demonstrate the practical utility of DeepER-Med through eight real-world clinical cases. Human clinician assessment indicates that DeepER-Med's conclusions align with clinical recommendations in seven cases, highlighting its potential for medical research and decision support. △ Less

Submitted 16 April, 2026; originally announced April 2026.

Comments: 37 pages, 6 figures, 5 tables

Dynamic Multimodal Expression Generation for LLM-Driven Pedagogical Agents: From User Experience Perspective

Authors: Ninghao Wan, Jiarun Song, Fuzheng Yang

Abstract: In virtual reality (VR) educational scenarios, Pedagogical agents (PAs) enhance immersive learning through realistic appearances and interactive behaviors. However, most existing PAs rely on static speech and simple gestures. This limitation reduces their ability to dynamically adapt to the semantic context of instructional content. As a result, interactions often lack naturalness and effectivenes… ▽ More In virtual reality (VR) educational scenarios, Pedagogical agents (PAs) enhance immersive learning through realistic appearances and interactive behaviors. However, most existing PAs rely on static speech and simple gestures. This limitation reduces their ability to dynamically adapt to the semantic context of instructional content. As a result, interactions often lack naturalness and effectiveness in the teaching process. To address this challenge, this study proposes a large language model (LLM)-driven multimodal expression generation method that constructs semantically sensitive prompts to generate coordinated speech and gesture instructions, enabling dynamic alignment between instructional semantics and multimodal expressive behaviors. A VR-based PA prototype was developed and evaluated through user experience-oriented subjective experiments. Results indicate that dynamically generated multimodal expressions significantly enhance learners' perceived learning effectiveness, engagement, and intention to use, while effectively alleviating feelings of fatigue and boredom during the learning process. Furthermore, the combined dynamic expression of speech and gestures notably enhances learners' perceptions of human-likeness and social presence. The findings provide new insights and design guidelines for building more immersive and naturally expressive intelligent PAs. △ Less

Submitted 10 March, 2026; originally announced March 2026.

TPIFM: A Task-Aware Model for Evaluating Perceptual Interaction Fluency in Remote AR Collaboration

Authors: Jiarun Song, Ninghao Wan, Fuzheng Yang, Weisi Lin

Abstract: Remote Collaborative Augmented Reality (RCAR) enables geographically distributed users to collaborate by integrating virtual and physical environments. However, because RCAR relies on real-time transmission, it is susceptible to delay and stalling impairments under constrained network conditions. Perceptual interaction fluency (PIF), defined as the perceived pace and responsiveness of collaboratio… ▽ More Remote Collaborative Augmented Reality (RCAR) enables geographically distributed users to collaborate by integrating virtual and physical environments. However, because RCAR relies on real-time transmission, it is susceptible to delay and stalling impairments under constrained network conditions. Perceptual interaction fluency (PIF), defined as the perceived pace and responsiveness of collaboration, is influenced not only by physical network impairments but also by intrinsic task characteristics. These characteristics can be interpreted as the task-specific just-noticeable difference (JND), i.e., the maximal tolerable temporal responsiveness before PIF degrades. When the average response time (ART), measured as the mean time per operation from receiving collaborator feedback to initiating the next action, falls within the JND, PIF is generally sustained, whereas values exceeding it indicate disruption. Tasks differ in their JNDs, reflecting distinct temporal responsiveness demands and sensitivities to impairments. From the perspective of the Free Energy Principle (FEP), tasks with lower JNDs impose stricter temporal prediction demands, making PIF more vulnerable to impairments, whereas higher JNDs allow greater tolerance. On this basis, we classify RCAR tasks by JND and evaluate their PIF through controlled subjective experiments under delay, stalling, and hybrid conditions. Building on these findings, we propose the Task-Aware Perceptual Interaction Fluency Model (TPIFM). Experimental results show that TPIFM accurately assesses PIF under network impairments, providing guidance for adaptive RCAR design and user experience optimization under network constraints. △ Less

Submitted 10 March, 2026; originally announced March 2026.

From Perception to Cognition: How Latency Affects Interaction Fluency and Social Presence in VR Conferencing

Authors: Jiarun Song, Ninghao Wan, FuZheng Yang, Weisi Lin

Abstract: Virtual reality (VR) conferencing has the potential to provide geographically dispersed users with an immersive environment, enabling rich social interactions and user experience using avatars. However, remote communication in VR inevitably introduces end-to-end (E2E) latency, which can significantly impact user experience. To clarify the impact of latency, we conducted subjective experiments to a… ▽ More Virtual reality (VR) conferencing has the potential to provide geographically dispersed users with an immersive environment, enabling rich social interactions and user experience using avatars. However, remote communication in VR inevitably introduces end-to-end (E2E) latency, which can significantly impact user experience. To clarify the impact of latency, we conducted subjective experiments to analyze how it influences interaction fluency from the perspective of quality perception and social presence from the perspective of social cognition, comparing VR conferencing with traditional video conferencing (VC). Specifically, interaction fluency emphasizes user perception of interaction pace and responsiveness and is assessed using Absolute Category Rating (ACR) method. In contrast, social presence focuses on the cognitive understanding of interaction, specifically whether individuals can comprehend the intentions, emotions, and behaviors expressed by others. It is primarily measured using the Networked Minds Social Presence Inventory (NMSPI). Building on this analysis, we further investigate the relationship between interaction fluency and social presence under different latency conditions to clarify the underlying perceptual and cognitive mechanisms. The findings from these subjective tests provide meaningful insights for optimizing the related systems, helping to improve interaction fluency and enhancing social presence in immersive virtual environments. △ Less

Submitted 10 March, 2026; originally announced March 2026.

Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution

Authors: Qiao Jin, Yin Fang, Lauren He, Yifan Yang, Guangzhi Xiong, Zhizheng Wang, Nicholas Wan, Joey Chan, Donald C. Comeau, Robert Leaman, Charalampos S. Floudas, Aidong Zhang, Michael F. Chiang, Yifan Peng, Zhiyong Lu

Abstract: Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the potential to automate this task, achieving strong performance requires frontier models such as GPT-5 that are prohibitively expensive to deploy at scale. To efficiently perform biomedical evidence attribution, we present Med-V1, a family of… ▽ More Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the potential to automate this task, achieving strong performance requires frontier models such as GPT-5 that are prohibitively expensive to deploy at scale. To efficiently perform biomedical evidence attribution, we present Med-V1, a family of small language models with only three billion parameters. Trained on high-quality synthetic data newly developed in this study, Med-V1 substantially outperforms (+27.0% to +71.3%) its base models on five biomedical benchmarks unified into a verification format. Despite its smaller size, Med-V1 performs comparably to frontier LLMs such as GPT-5, along with high-quality explanations for its predictions. We use Med-V1 to conduct a first-of-its-kind use case study that quantifies hallucinations in LLM-generated answers under different citation instructions. Results show that the format instruction strongly affects citation validity and hallucination, with GPT-5 generating more claims but exhibiting hallucination rates similar to GPT-4o. Additionally, we present a second use case showing that Med-V1 can automatically identify high-stakes evidence misattributions in clinical practice guidelines, revealing potentially negative public health impacts that are otherwise challenging to identify at scale. Overall, Med-V1 provides an efficient and accurate lightweight alternative to frontier LLMs for practical and real-world applications in biomedical evidence attribution and verification tasks. Med-V1 is available at https://github.com/ncbi-nlp/Med-V1. △ Less

Submitted 31 May, 2026; v1 submitted 5 March, 2026; originally announced March 2026.

SpectralTrain: A Universal Framework for Hyperspectral Image Classification

Authors: Meihua Zhou, Liping Yu, Xinyu Tong, Wai Kin Fung, Ruiguo Hu, Jiarui Zhao, Nan Wan

Abstract: Hyperspectral image (HSI) classification typically involves large-scale data and computationally intensive training, which limits the practical deployment of deep learning models in real-world remote sensing tasks. This study introduces SpectralTrain, a universal, architecture-agnostic training framework that enhances learning efficiency by integrating curriculum learning (CL) with principal compo… ▽ More Hyperspectral image (HSI) classification typically involves large-scale data and computationally intensive training, which limits the practical deployment of deep learning models in real-world remote sensing tasks. This study introduces SpectralTrain, a universal, architecture-agnostic training framework that enhances learning efficiency by integrating curriculum learning (CL) with principal component analysis (PCA)-based spectral downsampling. By gradually introducing spectral complexity while preserving essential information, SpectralTrain enables efficient learning of spectral -- spatial patterns at significantly reduced computational costs. The framework is independent of specific architectures, optimizers, or loss functions and is compatible with both classical and state-of-the-art (SOTA) models. Extensive experiments on three benchmark datasets -- Indian Pines, Salinas-A, and the newly introduced CloudPatch-7 -- demonstrate strong generalization across spatial scales, spectral characteristics, and application domains. The results indicate consistent reductions in training time by 2-7x speedups with small-to-moderate accuracy deltas depending on backbone. Its application to cloud classification further reveals potential in climate-related remote sensing, emphasizing training strategy optimization as an effective complement to architectural design in HSI models. Code is available at https://github.com/mh-zhou/SpectralTrain. △ Less

Submitted 29 May, 2026; v1 submitted 20 November, 2025; originally announced November 2025.

DCL-SE: Dynamic Curriculum Learning for Spatiotemporal Encoding of Brain Imaging

Authors: Meihua Zhou, Xinyu Tong, Jiarui Zhao, Min Cheng, Li Yang, Lei Tian, Nan Wan

Abstract: High-dimensional neuroimaging analyses for clinical diagnosis are often constrained by compromises in spatiotemporal fidelity and by the limited adaptability of large-scale, general-purpose models. To address these challenges, we introduce Dynamic Curriculum Learning for Spatiotemporal Encoding (DCL-SE), an end-to-end framework centered on data-driven spatiotemporal encoding (DaSE). We leverage Ap… ▽ More High-dimensional neuroimaging analyses for clinical diagnosis are often constrained by compromises in spatiotemporal fidelity and by the limited adaptability of large-scale, general-purpose models. To address these challenges, we introduce Dynamic Curriculum Learning for Spatiotemporal Encoding (DCL-SE), an end-to-end framework centered on data-driven spatiotemporal encoding (DaSE). We leverage Approximate Rank Pooling (ARP) to efficiently encode three-dimensional volumetric brain data into information-rich, two-dimensional dynamic representations, and then employ a dynamic curriculum learning strategy, guided by a Dynamic Group Mechanism (DGM), to progressively train the decoder, refining feature extraction from global anatomical structures to fine pathological details. Evaluated across six publicly available datasets, including Alzheimer's disease and brain tumor classification, cerebral artery segmentation, and brain age prediction, DCL-SE consistently outperforms existing methods in accuracy, robustness, and interpretability. These findings underscore the critical importance of compact, task-specific architectures in the era of large-scale pretrained networks. △ Less

Submitted 19 November, 2025; originally announced November 2025.

Designing a Secure and Resilient Distributed Smartphone Participant Data Collection System

Authors: Foad Namjoo, Neng Wan, Devan Mallory, Yuyi Chang, Nithin Sugavanam, Long Yin Lee, Ning Xiong, Emre Ertin, Jeff M. Phillips

Abstract: Real-world health studies require continuous and secure data collection from mobile and wearable devices. We introduce MotionPI, a smartphone-based system designed to collect behavioral and health data through sensors and surveys with minimal interaction from participants. The system integrates passive data collection (such as GPS and wristband motion data) with Ecological Momentary Assessment (EM… ▽ More Real-world health studies require continuous and secure data collection from mobile and wearable devices. We introduce MotionPI, a smartphone-based system designed to collect behavioral and health data through sensors and surveys with minimal interaction from participants. The system integrates passive data collection (such as GPS and wristband motion data) with Ecological Momentary Assessment (EMA) surveys, which can be triggered randomly or based on physical activity. MotionPI is designed to work under real-life constraints, including limited battery life, weak or intermittent cellular connection, and minimal user supervision. It stores data both locally and on a secure cloud server, with encrypted transmission and storage. It integrates through Bluetooth Low Energy (BLE) into wristband devices that store raw data and communicate motion summaries and trigger events. MotionPI demonstrates a practical solution for secure and scalable mobile data collection in cyber-physical health studies. △ Less

Submitted 22 October, 2025; originally announced October 2025.

Comments: 9 pages, 3 figures. Accepted at EAI SmartSP 2025 Conference (Springer LNICST). This version is the arXiv preprint prepared for open access

Recommending Clinical Trials for Online Patient Cases using Artificial Intelligence

Authors: Joey Chan, Qiao Jin, Nicholas Wan, Charalampos S. Floudas, Elisabetta Xue, Zhiyong Lu

Abstract: Clinical trials are crucial for assessing new treatments; however, recruitment challenges - such as limited awareness, complex eligibility criteria, and referral barriers - hinder their success. With the growth of online platforms, patients increasingly turn to social media and health communities for support, research, and advocacy, expanding recruitment pools and established enrollment pathways.… ▽ More Clinical trials are crucial for assessing new treatments; however, recruitment challenges - such as limited awareness, complex eligibility criteria, and referral barriers - hinder their success. With the growth of online platforms, patients increasingly turn to social media and health communities for support, research, and advocacy, expanding recruitment pools and established enrollment pathways. Recognizing this potential, we utilized TrialGPT, a framework that leverages a large language model (LLM) as its backbone, to match 50 online patient cases (collected from published case reports and a social media website) to clinical trials and evaluate performance against traditional keyword-based searches. Our results show that TrialGPT outperforms traditional methods by 46% in identifying eligible trials, with each patient, on average, being eligible for around 7 trials. Additionally, our outreach efforts to case authors and trial organizers regarding these patient-trial matches yielded highly positive feedback, which we present from both perspectives. △ Less

Submitted 15 April, 2025; originally announced April 2025.

Comments: 10 pages with 2 figures and 2 tables

A foundation model for human-AI collaboration in medical literature mining

Authors: Zifeng Wang, Lang Cao, Qiao Jin, Joey Chan, Nicholas Wan, Behdad Afzali, Hyun-Jin Cho, Chang-In Choi, Mehdi Emamverdi, Manjot K. Gill, Sun-Hyung Kim, Yijia Li, Yi Liu, Hanley Ong, Justin Rousseau, Irfan Sheikh, Jenny J. Wei, Ziyang Xu, Christopher M. Zallek, Kyungsang Kim, Yifan Peng, Zhiyong Lu, Jimeng Sun

Abstract: Systematic literature review is essential for evidence-based medicine, requiring comprehensive analysis of clinical trial publications. However, the application of artificial intelligence (AI) models for medical literature mining has been limited by insufficient training and evaluation across broad therapeutic areas and diverse tasks. Here, we present LEADS, an AI foundation model for study search… ▽ More Systematic literature review is essential for evidence-based medicine, requiring comprehensive analysis of clinical trial publications. However, the application of artificial intelligence (AI) models for medical literature mining has been limited by insufficient training and evaluation across broad therapeutic areas and diverse tasks. Here, we present LEADS, an AI foundation model for study search, screening, and data extraction from medical literature. The model is trained on 633,759 instruction data points in LEADSInstruct, curated from 21,335 systematic reviews, 453,625 clinical trial publications, and 27,015 clinical trial registries. We showed that LEADS demonstrates consistent improvements over four cutting-edge generic large language models (LLMs) on six tasks. Furthermore, LEADS enhances expert workflows by providing supportive references following expert requests, streamlining processes while maintaining high-quality results. A study with 16 clinicians and medical researchers from 14 different institutions revealed that experts collaborating with LEADS achieved a recall of 0.81 compared to 0.77 experts working alone in study selection, with a time savings of 22.6%. In data extraction tasks, experts using LEADS achieved an accuracy of 0.85 versus 0.80 without using LEADS, alongside a 26.9% time savings. These findings highlight the potential of specialized medical literature foundation models to outperform generic models, delivering significant quality and efficiency benefits when integrated into expert workflows for medical literature mining. △ Less

Submitted 27 January, 2025; originally announced January 2025.

Humans and Large Language Models in Clinical Decision Support: A Study with Medical Calculators

Authors: Nicholas Wan, Qiao Jin, Joey Chan, Guangzhi Xiong, Serina Applebaum, Aidan Gilson, Reid McMurry, R. Andrew Taylor, Aidong Zhang, Qingyu Chen, Zhiyong Lu

Abstract: Although large language models (LLMs) have been assessed for general medical knowledge using licensing exams, their ability to support clinical decision-making, such as selecting medical calculators, remains uncertain. We assessed nine LLMs, including open-source, proprietary, and domain-specific models, with 1,009 multiple-choice question-answer pairs across 35 clinical calculators and compared L… ▽ More Although large language models (LLMs) have been assessed for general medical knowledge using licensing exams, their ability to support clinical decision-making, such as selecting medical calculators, remains uncertain. We assessed nine LLMs, including open-source, proprietary, and domain-specific models, with 1,009 multiple-choice question-answer pairs across 35 clinical calculators and compared LLMs to humans on a subset of questions. While the highest-performing LLM, OpenAI o1, provided an answer accuracy of 66.0% (CI: 56.7-75.3%) on the subset of 100 questions, two human annotators nominally outperformed LLMs with an average answer accuracy of 79.5% (CI: 73.5-85.0%). Ultimately, we evaluated medical trainees and LLMs in recommending medical calculators across clinical scenarios like risk stratification and diagnosis. With error analysis showing that the highest-performing LLMs continue to make mistakes in comprehension (49.3% of errors) and calculator knowledge (7.1% of errors), our findings highlight that LLMs are not superior to humans in calculator recommendation. △ Less

Submitted 21 March, 2025; v1 submitted 8 November, 2024; originally announced November 2024.

Comments: 10 pages, 3 figures, 2 tables

Entry-level guide to the use of large language models for medical research

Authors: Qiao Jin, Nicholas Wan, Robert Leaman, Shubo Tian, Zhizheng Wang, Yifan Yang, Zifeng Wang, Guangzhi Xiong, Po-Ting Lai, Qingqing Zhu, Benjamin Hou, Maame Sarfo-Gyamfi, Gongbo Zhang, Aidan Gilson, Balu Bhasuran, Zhe He, Aidong Zhang, Jimeng Sun, Chunhua Weng, Ronald M. Summers, Qingyu Chen, Yifan Peng, Zhiyong Lu

Abstract: Frontier large language models (LLMs), such as GPT-5, Claude 4.5, Gemini 3, Llama 4, and DeepSeek-R1, represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare by generating human-like responses across diverse contexts and adapting to novel tasks following human instructions. Their potential application spans a broad range of medical tasks, such as clini… ▽ More Frontier large language models (LLMs), such as GPT-5, Claude 4.5, Gemini 3, Llama 4, and DeepSeek-R1, represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare by generating human-like responses across diverse contexts and adapting to novel tasks following human instructions. Their potential application spans a broad range of medical tasks, such as clinical documentation, matching patients to clinical trials, and answering medical questions. In this paper, we propose an actionable guideline to help healthcare professionals more effectively and efficiently utilize LLMs in their work, along with a set of best practices. The overall workflow consists of several main phases, including formulating the task, choosing LLMs, prompt engineering, fine-tuning, and model deployment. We start with the discussion of critical considerations in identifying medical tasks that align with the core capabilities of LLMs and selecting models based on the selected task and data, performance requirements, and model interface. We then review the strategies, such as prompt engineering and fine-tuning, to adapt standard LLMs to specialized medical tasks. Deployment considerations, including regulatory compliance, ethical guidelines, and continuous monitoring for fairness and bias, are also discussed. By providing a structured step-by-step methodology, this entry-level tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice, ensuring that these powerful technologies are applied in a safe, reliable, and impactful manner. △ Less

Submitted 18 May, 2026; v1 submitted 24 October, 2024; originally announced October 2024.

Beyond Multiple-Choice Accuracy: Real-World Challenges of Implementing Large Language Models in Healthcare

Authors: Yifan Yang, Qiao Jin, Qingqing Zhu, Zhizheng Wang, Francisco Erramuspe Álvarez, Nicholas Wan, Benjamin Hou, Zhiyong Lu

Abstract: Large Language Models (LLMs) have gained significant attention in the medical domain for their human-level capabilities, leading to increased efforts to explore their potential in various healthcare applications. However, despite such a promising future, there are multiple challenges and obstacles that remain for their real-world uses in practical settings. This work discusses key challenges for L… ▽ More Large Language Models (LLMs) have gained significant attention in the medical domain for their human-level capabilities, leading to increased efforts to explore their potential in various healthcare applications. However, despite such a promising future, there are multiple challenges and obstacles that remain for their real-world uses in practical settings. This work discusses key challenges for LLMs in medical applications from four unique aspects: operational vulnerabilities, ethical and social considerations, performance and assessment difficulties, and legal and regulatory compliance. Addressing these challenges is crucial for leveraging LLMs to their full potential and ensuring their responsible integration into healthcare. △ Less

Submitted 24 October, 2024; originally announced October 2024.

New Insights into Global Warming: End-to-End Visual Analysis and Prediction of Temperature Variations

Authors: Meihua Zhou, Nan Wan, Tianlong Zheng, Hanwen Xu, Li Yang, Tingting Wang

Abstract: Global warming presents an unprecedented challenge to our planet however comprehensive understanding remains hindered by geographical biases temporal limitations and lack of standardization in existing research. An end to end visual analysis of global warming using three distinct temperature datasets is presented. A baseline adjusted from the Paris Agreements one point five degrees Celsius benchma… ▽ More Global warming presents an unprecedented challenge to our planet however comprehensive understanding remains hindered by geographical biases temporal limitations and lack of standardization in existing research. An end to end visual analysis of global warming using three distinct temperature datasets is presented. A baseline adjusted from the Paris Agreements one point five degrees Celsius benchmark based on data analysis is employed. A closed loop design from visualization to prediction and clustering is created using classic models tailored to the characteristics of the data. This approach reduces complexity and eliminates the need for advanced feature engineering. A lightweight convolutional neural network and long short term memory model specifically designed for global temperature change is proposed achieving exceptional accuracy in long term forecasting with a mean squared error of three times ten to the power of negative six and an R squared value of zero point nine nine nine nine. Dynamic time warping and KMeans clustering elucidate national level temperature anomalies and carbon emission patterns. This comprehensive method reveals intricate spatiotemporal characteristics of global temperature variations and provides warming trend attribution. The findings offer new insights into climate change dynamics demonstrating that simplicity and precision can coexist in environmental analysis. △ Less

Submitted 18 September, 2025; v1 submitted 12 September, 2024; originally announced September 2024.

Comments: 28 pages

An Information-Theoretic Analysis of Discrete-Time Control and Filtering Limitations by the I-MMSE Relationships

Authors: Neng Wan, Dapeng Li, Naira Hovakimyan, Petros G. Voulgaris

Abstract: Fundamental limitations or performance trade-offs/limits are important properties and constraints of both control and filtering systems. Among various trade-off metrics, total information rate that characterizes the sensitivity trade-offs and time-averaged performance of control and filtering systems was conventionally studied by using the differential entropy rate and Kolmogorov-Bode formula. In… ▽ More Fundamental limitations or performance trade-offs/limits are important properties and constraints of both control and filtering systems. Among various trade-off metrics, total information rate that characterizes the sensitivity trade-offs and time-averaged performance of control and filtering systems was conventionally studied by using the differential entropy rate and Kolmogorov-Bode formula. In this paper, by extending the famous I-MMSE (mutual information -- minimum mean-square error) relationships to the discrete-time additive white Gaussian channels with and without feedback, a new paradigm is introduced to estimate and analyze total information rate as a control and filtering trade-off metric. Under this framework, we explore the trade-off properties of total information rate for a variety of the discrete-time control and filtering systems, e.g., LTI, LTV, and nonlinear, and propose an alternative approach to investigate total information rate via optimal estimation. △ Less

Submitted 17 March, 2025; v1 submitted 18 April, 2023; originally announced April 2023.

Comments: This manuscript is the extended version of the paper with the same title accepted by IEEE Transactions on Automatic Control. Neng Wan and Dapeng Li contributed equally to this paper

LostNet: A smart way for lost and find

Authors: Meihua Zhou, Ivan Fung, Li Yang, Nan Wan, Keke Di, Tingting Wang

Abstract: Due to the enormous population growth of cities in recent years, objects are frequently lost and unclaimed on public transportation, in restaurants, or any other public areas. While services like Find My iPhone can easily identify lost electronic devices, more valuable objects cannot be tracked in an intelligent manner, making it impossible for administrators to reclaim a large number of lost and… ▽ More Due to the enormous population growth of cities in recent years, objects are frequently lost and unclaimed on public transportation, in restaurants, or any other public areas. While services like Find My iPhone can easily identify lost electronic devices, more valuable objects cannot be tracked in an intelligent manner, making it impossible for administrators to reclaim a large number of lost and found items in a timely manner. We present a method that significantly reduces the complexity of searching by comparing previous images of lost and recovered things provided by the owner with photos taken when registered lost and found items are received. In this research, we will primarily design a photo matching network by combining the fine-tuning method of MobileNetv2 with CBAM Attention and using the Internet framework to develop an online lost and found image identification system. Our implementation gets a testing accuracy of 96.8% using only 665.12M GLFOPs and 3.5M training parameters. It can recognize practice images and can be run on a regular laptop. △ Less

Submitted 5 January, 2023; originally announced January 2023.

Safety Embedded Stochastic Optimal Control of Networked Multi-Agent Systems via Barrier States

Authors: Lin Song, Pan Zhao, Neng Wan, Naira Hovakimyan

Abstract: This paper presents a novel approach for achieving safe stochastic optimal control in networked multi-agent systems (MASs). The proposed method incorporates barrier states (BaSs) into the system dynamics to embed safety constraints. To accomplish this, the networked MAS is factorized into multiple subsystems, and each one is augmented with BaSs for the central agent. The optimal control law is obt… ▽ More This paper presents a novel approach for achieving safe stochastic optimal control in networked multi-agent systems (MASs). The proposed method incorporates barrier states (BaSs) into the system dynamics to embed safety constraints. To accomplish this, the networked MAS is factorized into multiple subsystems, and each one is augmented with BaSs for the central agent. The optimal control law is obtained by solving the joint Hamilton-Jacobi-Bellman (HJB) equation on the augmented subsystem, which guarantees safety via the boundedness of the BaSs. The BaS-based optimal control technique yields safe control actions while maintaining optimality. The safe optimal control solution is approximated using path integrals. To validate the effectiveness of the proposed approach, numerical simulations are conducted on a cooperative UAV team in two different scenarios. △ Less

Submitted 3 April, 2023; v1 submitted 7 October, 2022; originally announced October 2022.

An Information-Theoretic Analysis of Continuous-Time Control and Filtering Limitations by the I-MMSE Relationships

Authors: Neng Wan, Dapeng Li, Naira Hovakimyan

Abstract: While information theory has been introduced to characterize the fundamental limitations of control and filtering for a few decades, the existing information-theoretic methods are indirect and cumbersome for analyzing the limitations of continuous-time systems. To answer this challenge, we lift the information-theoretic analysis to continuous function spaces by the I-MMSE relationships. Continuous… ▽ More While information theory has been introduced to characterize the fundamental limitations of control and filtering for a few decades, the existing information-theoretic methods are indirect and cumbersome for analyzing the limitations of continuous-time systems. To answer this challenge, we lift the information-theoretic analysis to continuous function spaces by the I-MMSE relationships. Continuous-time control and filtering systems are modeled into the additive Gaussian channels with and without feedback, and the total information rate is identified as a control and filtering trade-off metric and calculated from the estimation error of channel inputs. Fundamental constraints for this trade-off metric are first derived in a general setup and then used to capture the limitations of various control and filtering systems subject to linear and nonlinear plant models. For linear scenarios, we show that the total information rate quantifies the performance limits, such as the minimum entropy cost and the lowest achievable mean-square estimation error, in the time domain. For nonlinear systems, we provide a direct method to calculate and interpret the total information rate and its lower bound by the Stratonovich-Kushner equation. △ Less

Submitted 31 January, 2026; v1 submitted 4 January, 2022; originally announced January 2022.

Comments: This paper is the extended version of an article with the same title accepted for publication in Automatica. Dapeng Li and Neng Wan contributed equally to this work

Transformers for prompt-level EMA non-response prediction

Authors: Supriya Nagesh, Alexander Moreno, Stephanie M. Carpenter, Jamie Yap, Soujanya Chatterjee, Steven Lloyd Lizotte, Neng Wan, Santosh Kumar, Cho Lam, David W. Wetter, Inbal Nahum-Shani, James M. Rehg

Abstract: Ecological Momentary Assessments (EMAs) are an important psychological data source for measuring current cognitive states, affect, behavior, and environmental factors from participants in mobile health (mHealth) studies and treatment programs. Non-response, in which participants fail to respond to EMA prompts, is an endemic problem. The ability to accurately predict non-response could be utilized… ▽ More Ecological Momentary Assessments (EMAs) are an important psychological data source for measuring current cognitive states, affect, behavior, and environmental factors from participants in mobile health (mHealth) studies and treatment programs. Non-response, in which participants fail to respond to EMA prompts, is an endemic problem. The ability to accurately predict non-response could be utilized to improve EMA delivery and develop compliance interventions. Prior work has explored classical machine learning models for predicting non-response. However, as increasingly large EMA datasets become available, there is the potential to leverage deep learning models that have been effective in other fields. Recently, transformer models have shown state-of-the-art performance in NLP and other domains. This work is the first to explore the use of transformers for EMA data analysis. We address three key questions in applying transformers to EMA data: 1. Input representation, 2. encoding temporal information, 3. utility of pre-training on improving downstream prediction task performance. The transformer model achieves a non-response prediction AUC of 0.77 and is significantly better than classical ML and LSTM-based deep learning models. We will make our a predictive model trained on a corpus of 40K EMA samples freely-available to the research community, in order to facilitate the development of future transformer-based EMA analysis works. △ Less

Submitted 1 November, 2021; originally announced November 2021.

Distributed Algorithms for Linearly-Solvable Optimal Control in Networked Multi-Agent Systems

Authors: Neng Wan, Aditya Gahlawat, Naira Hovakimyan, Evangelos A. Theodorou, Petros G. Voulgaris

Abstract: Distributed algorithms for both discrete-time and continuous-time linearly solvable optimal control (LSOC) problems of networked multi-agent systems (MASs) are investigated in this paper. A distributed framework is proposed to partition the optimal control problem of a networked MAS into several local optimal control problems in factorial subsystems, such that each (central) agent behaves optimall… ▽ More Distributed algorithms for both discrete-time and continuous-time linearly solvable optimal control (LSOC) problems of networked multi-agent systems (MASs) are investigated in this paper. A distributed framework is proposed to partition the optimal control problem of a networked MAS into several local optimal control problems in factorial subsystems, such that each (central) agent behaves optimally to minimize the joint cost function of a subsystem that comprises a central agent and its neighboring agents, and the local control actions (policies) only rely on the knowledge of local observations. Under this framework, we not only preserve the correlations between neighboring agents, but moderate the communication and computational complexities by decentralizing the sampling and computational processes over the network. For discrete-time systems modeled by Markov decision processes, the joint Bellman equation of each subsystem is transformed into a system of linear equations and solved using parallel programming. For continuous-time systems modeled by Itô diffusion processes, the joint optimality equation of each subsystem is converted into a linear partial differential equation, whose solution is approximated by a path integral formulation and a sample-efficient relative entropy policy search algorithm, respectively. The learned control policies are generalized to solve the unlearned tasks by resorting to the compositionality principle, and illustrative examples of cooperative UAV teams are provided to verify the effectiveness and advantages of these algorithms. △ Less

Submitted 17 February, 2021; originally announced February 2021.

Cooperative Path Integral Control for Stochastic Multi-Agent Systems

Authors: Neng Wan, Aditya Gahlawat, Naira Hovakimyan, Evangelos A. Theodorou, Petros G. Voulgaris

Abstract: A distributed stochastic optimal control solution is presented for cooperative multi-agent systems. The network of agents is partitioned into multiple factorial subsystems, each of which consists of a central agent and neighboring agents. Local control actions that rely only on agents' local observations are designed to optimize the joint cost functions of subsystems. When solving for the local co… ▽ More A distributed stochastic optimal control solution is presented for cooperative multi-agent systems. The network of agents is partitioned into multiple factorial subsystems, each of which consists of a central agent and neighboring agents. Local control actions that rely only on agents' local observations are designed to optimize the joint cost functions of subsystems. When solving for the local control actions, the joint optimality equation for each subsystem is cast as a linear partial differential equation and solved using the Feynman-Kac formula. The solution and the optimal control action are then formulated as path integrals and approximated by a Monte-Carlo method. Numerical verification is provided through a simulation example consisting of a team of cooperative UAVs. △ Less

Submitted 20 March, 2021; v1 submitted 30 September, 2020; originally announced September 2020.

Comments: To appear in American Control Conference 2021, New Orleans, LA, USA

Compositionality of Linearly Solvable Optimal Control in Networked Multi-Agent Systems

Authors: Lin Song, Neng Wan, Aditya Gahlawat, Naira Hovakimyan, Evangelos A. Theodorou

Abstract: In this paper, we discuss the methodology of generalizing the optimal control law from learned component tasks to unlearned composite tasks on Multi-Agent Systems (MASs), by using the linearity composition principle of linearly solvable optimal control (LSOC) problems. The proposed approach achieves both the compositionality and optimality of control actions simultaneously within the cooperative M… ▽ More In this paper, we discuss the methodology of generalizing the optimal control law from learned component tasks to unlearned composite tasks on Multi-Agent Systems (MASs), by using the linearity composition principle of linearly solvable optimal control (LSOC) problems. The proposed approach achieves both the compositionality and optimality of control actions simultaneously within the cooperative MAS framework in both discrete- and continuous-time in a sample-efficient manner, which reduces the burden of re-computation of the optimal control solutions for the new task on the MASs. We investigate the application of the proposed approach on the MAS with coordination between agents. The experiments show feasible results in investigated scenarios, including both discrete and continuous dynamical systems for task generalization without resampling. △ Less

Submitted 22 March, 2021; v1 submitted 28 September, 2020; originally announced September 2020.

Comments: Accepted to the 2021 American Control Conference (ACC)

f-Divergence Variational Inference

Authors: Neng Wan, Dapeng Li, Naira Hovakimyan

Abstract: This paper introduces the $f$-divergence variational inference ($f$-VI) that generalizes variational inference to all $f$-divergences. Initiated from minimizing a crafty surrogate $f$-divergence that shares the statistical consistency with the $f$-divergence, the $f$-VI framework not only unifies a number of existing VI methods, e.g. Kullback-Leibler VI, Rényi's $α$-VI, and $χ$-VI, but offers a st… ▽ More This paper introduces the $f$-divergence variational inference ($f$-VI) that generalizes variational inference to all $f$-divergences. Initiated from minimizing a crafty surrogate $f$-divergence that shares the statistical consistency with the $f$-divergence, the $f$-VI framework not only unifies a number of existing VI methods, e.g. Kullback-Leibler VI, Rényi's $α$-VI, and $χ$-VI, but offers a standardized toolkit for VI subject to arbitrary divergences from $f$-divergence family. A general $f$-variational bound is derived and provides a sandwich estimate of marginal likelihood (or evidence). The development of the $f$-VI unfolds with a stochastic optimization scheme that utilizes the reparameterization trick, importance weighting and Monte Carlo approximation; a mean-field approximation scheme that generalizes the well-known coordinate ascent variational inference (CAVI) is also proposed for $f$-VI. Empirical examples, including variational autoencoders and Bayesian neural networks, are provided to demonstrate the effectiveness and the wide applicability of $f$-VI. △ Less

Submitted 3 April, 2021; v1 submitted 28 September, 2020; originally announced September 2020.

Comments: Dapeng Li and Neng Wan contributed equally to this paper. Supplementary material is attached. The links to code are provided in the paper, supplementary material and reference list. To appear in Advances in Neural Information Processing Systems 33 (NeurIPS 2020)

Bridging the Generalization Gap: Training Robust Models on Confounded Biological Data

Authors: Tzu-Yu Liu, Ajay Kannan, Adam Drake, Marvin Bertin, Nathan Wan

Abstract: Statistical learning on biological data can be challenging due to confounding variables in sample collection and processing. Confounders can cause models to generalize poorly and result in inaccurate prediction performance metrics if models are not validated thoroughly. In this paper, we propose methods to control for confounding factors and further improve prediction performance. We introduce Ort… ▽ More Statistical learning on biological data can be challenging due to confounding variables in sample collection and processing. Confounders can cause models to generalize poorly and result in inaccurate prediction performance metrics if models are not validated thoroughly. In this paper, we propose methods to control for confounding factors and further improve prediction performance. We introduce OrthoNormal basis construction In cOnfounding factor Normalization (ONION) to remove confounding covariates and use the Domain-Adversarial Neural Network (DANN) to penalize models for encoding confounder information. We apply the proposed methods to simulated and empirical patient data and show significant improvements in generalization. △ Less

Submitted 11 December, 2018; originally announced December 2018.

METCC: METric learning for Confounder Control Making distance matter in high dimensional biological analysis

Authors: Kabir Manghnani, Adam Drake, Nathan Wan, Imran Haque

Abstract: High-dimensional data acquired from biological experiments such as next generation sequencing are subject to a number of confounding effects. These effects include both technical effects, such as variation across batches from instrument noise or sample processing, or institution-specific differences in sample acquisition and physical handling, as well as biological effects arising from true but ir… ▽ More High-dimensional data acquired from biological experiments such as next generation sequencing are subject to a number of confounding effects. These effects include both technical effects, such as variation across batches from instrument noise or sample processing, or institution-specific differences in sample acquisition and physical handling, as well as biological effects arising from true but irrelevant differences in the biology of each sample, such as age biases in diseases. Prior work has used linear methods to adjust for such batch effects. Here, we apply contrastive metric learning by a non-linear triplet network to optimize the ability to distinguish biologically distinct sample classes in the presence of irrelevant technical and biological variation. Using whole-genome cell-free DNA data from 817 patients, we demonstrate that our approach, METric learning for Confounder Control (METCC), is able to match or exceed the classification performance achieved using a best-in-class linear method (HCP) or no normalization. Critically, results from METCC appear less confounded by irrelevant technical variables like institution and batch than those from other methods even without access to high quality metadata information required by many existing techniques; offering hope for improved generalization. △ Less

Submitted 7 December, 2018; originally announced December 2018.

Comments: Machine Learning for Health (ML4H) Workshop at NeurIPS 2018

Report number: ML4H/2018/211

Speech recognition for medical conversations

Authors: Chung-Cheng Chiu, Anshuman Tripathi, Katherine Chou, Chris Co, Navdeep Jaitly, Diana Jaunzeikare, Anjuli Kannan, Patrick Nguyen, Hasim Sak, Ananth Sankar, Justin Tansuwan, Nathan Wan, Yonghui Wu, Xuedong Zhang

Abstract: In this work we explored building automatic speech recognition models for transcribing doctor patient conversation. We collected a large scale dataset of clinical conversations ($14,000$ hr), designed the task to represent the real word scenario, and explored several alignment approaches to iteratively improve data quality. We explored both CTC and LAS systems for building speech recognition model… ▽ More In this work we explored building automatic speech recognition models for transcribing doctor patient conversation. We collected a large scale dataset of clinical conversations ($14,000$ hr), designed the task to represent the real word scenario, and explored several alignment approaches to iteratively improve data quality. We explored both CTC and LAS systems for building speech recognition models. The LAS was more resilient to noisy data and CTC required more data clean up. A detailed analysis is provided for understanding the performance for clinical tasks. Our analysis showed the speech recognition models performed well on important medical utterances, while errors occurred in causal conversations. Overall we believe the resulting models can provide reasonable quality in practice. △ Less

Submitted 20 June, 2018; v1 submitted 20 November, 2017; originally announced November 2017.

Comments: Interspeech 2018 camera ready