IEEE PulsePub Date : 2026-01-01DOI: 10.1109/MPULS.2026.3659250
Ragib Shahariar Ayon, Shibbir Ahmed
{"title":"AutoJML: Generation and Verification of JML Specifications Using LLM Agents.","authors":"Ragib Shahariar Ayon, Shibbir Ahmed","doi":"10.1109/MPULS.2026.3659250","DOIUrl":"10.1109/MPULS.2026.3659250","url":null,"abstract":"<p><p>Formal specifications such as Java Modeling Language (JML) are essential for program verification, but are complex and error-prone to write manually. Although recent large language model (LLM) based approaches automate specification generation, they often struggle with complex control flow and semantic completeness. We present AutoJML, an LLM agent that generates and refines JML specifications using iterative verification and mutation-based feedback. Evaluated on Java programs with diverse control flow patterns, AutoJML verifies more programs than a state-of-the-art baseline, particularly for multipath and nested loop programs.</p>","PeriodicalId":49065,"journal":{"name":"IEEE Pulse","volume":"17 1","pages":"66-68"},"PeriodicalIF":1.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147950046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE PulsePub Date : 2026-01-01DOI: 10.1109/MPULS.2026.3659277
James McArdle, Martin Burtscher
{"title":"What Polynomial Regression Reveals About Scientific Data Compression.","authors":"James McArdle, Martin Burtscher","doi":"10.1109/MPULS.2026.3659277","DOIUrl":"10.1109/MPULS.2026.3659277","url":null,"abstract":"<p><p>Scientific instruments and large-scale simulations produce vast amounts of floating-point data, posing challenges for storage, transfer, and analysis. Modern lossy compression reduces data size within error limits but often obscures local data behavior. Consequently, compression is seen mainly as a tool for size reduction rather than a means of learning about the data. Polynomial regression offers another option. Fitting simple mathematical curves to small regions of data can both reduce data size and highlight features such as smooth trends, abrupt changes, and noisy regions. In this work, we examine piecewise polynomial regression as a structure-aware form of compression. Our goal is less about outperforming other compressors and more about showing how locally fitted models can expose the underlying structure of the data.</p>","PeriodicalId":49065,"journal":{"name":"IEEE Pulse","volume":"17 1","pages":"57-59"},"PeriodicalIF":1.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147950087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE PulsePub Date : 2026-01-01DOI: 10.1109/MPULS.2026.3659262
Jim Banks
{"title":"Finding Clarity in the Battle With Crohn's Disease.","authors":"Jim Banks","doi":"10.1109/MPULS.2026.3659262","DOIUrl":"https://doi.org/10.1109/MPULS.2026.3659262","url":null,"abstract":"<p><p>Early biologic therapy reshapes Crohn's outcomes as predictive biomarkers fall short.Crohn's disease is an increasingly prevalent but poorly understood condition. Data suggest that in the U.K. alone, 1 in 350 people have the disease and around 10,000 new cases are diagnosed each year, many of them young people. Treatment pathways traditionally take a bottom-up approach, starting with the steroids and moving up the 'therapeutic pyramid' through immunomodulators and then biologics such as infliximab and adalimumab. Nevertheless, a groundbreaking study in the U.K. by researchers at Cambridge University and NHS Trusts suggests that going for the stronger treatments early post-diagnosis might better control inflammation and, in the long run, be more cost-effective and yield better patient outcomes. Jim Banks investigates the pros and cons of changing the therapeutic pathway for a condition that keeps creating one conundrum after another.</p>","PeriodicalId":49065,"journal":{"name":"IEEE Pulse","volume":"17 1","pages":"6-9"},"PeriodicalIF":0.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147692921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE PulsePub Date : 2026-01-01DOI: 10.1109/MPULS.2026.3659240
Ahmad Elallaf, Yuktha Priya Masupalli, Gongbo Liang
{"title":"Uncertainty-Aware Vision-Language Learning Improves Chest X-Ray Retrieval.","authors":"Ahmad Elallaf, Yuktha Priya Masupalli, Gongbo Liang","doi":"10.1109/MPULS.2026.3659240","DOIUrl":"10.1109/MPULS.2026.3659240","url":null,"abstract":"<p><p>Vision-language foundation models have emerged as powerful general-purpose representation learners, but their deterministic embeddings often fail to provide the reliability required for high-stakes biomedical tasks. We introduce MedProbCLIP, a probabilistic vision-language learning framework for chest X-ray and radiology report representation learning and retrieval. Evaluated on the MIMIC-CXR dataset, MedProbCLIP outperforms deterministic and probabilistic baselines in both retrieval and zero-shot classification, while improving the trustworthiness significantly.</p>","PeriodicalId":49065,"journal":{"name":"IEEE Pulse","volume":"17 1","pages":"54-56"},"PeriodicalIF":0.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147950094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE PulsePub Date : 2026-01-01DOI: 10.1109/MPULS.2026.3659241
Chad Andresen
{"title":"Industry Corner Live With Adaptyx Co-Founder and CEO Vijit Sabnis.","authors":"Chad Andresen","doi":"10.1109/MPULS.2026.3659241","DOIUrl":"10.1109/MPULS.2026.3659241","url":null,"abstract":"<p><p>Exploring the next generation of sensing nano-scale biomarkers with Adaptyx's latest revolution in molecular switches.</p>","PeriodicalId":49065,"journal":{"name":"IEEE Pulse","volume":"17 1","pages":"38-46"},"PeriodicalIF":1.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147692899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE PulsePub Date : 2026-01-01DOI: 10.1109/MPULS.2026.3659249
Kamrul Hasan, Oleg V Komogortsev
{"title":"Diffusion Versus GAN for Subject-Specific Gaze Synthesis.","authors":"Kamrul Hasan, Oleg V Komogortsev","doi":"10.1109/MPULS.2026.3659249","DOIUrl":"10.1109/MPULS.2026.3659249","url":null,"abstract":"<p><p>Generating realistic, subject-specific eye movement signals is crucial for data augmentation, gaze-based authentication, privacy-preserving analytics, and robust gaze-based interfaces. Recent advances in deep learning have enabled the generation of synthetic gaze data, but individualized gaze sequence generation has been less explored, with most approaches relying on random noise distributions or predefined latent embeddings. In this work, our main contribution is the introduction of explicit subject-aware modifications to both diffusion and generative adversarial networks (GANs)-based methods for generating realistic, individualized synthetic gaze data. In particular, we equip the diffusion-based method with compact user embeddings to capture per-subject traits and enhance the GAN-based generator with a subject-specific synthesis module to better retain idiosyncratic gaze information. We comprehensively assess these subject-aware methods with standard eye-tracking signal quality metrics, including spatial accuracy and precision. This work defines synthetic signal quality, realism, and subject specificity, and advances the potential of subject-aware gaze-based applications.</p>","PeriodicalId":49065,"journal":{"name":"IEEE Pulse","volume":"17 1","pages":"60-62"},"PeriodicalIF":1.2,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147950068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE PulsePub Date : 2025-11-01DOI: 10.1109/MPULS.2025.3640837
Tyler S Oesterle, Nicholas L Bormann, Mark A Lifson, Katina Michael
{"title":"A Substance Use Disorder Virtual Treatment and Research Platform: A Proof of Concept.","authors":"Tyler S Oesterle, Nicholas L Bormann, Mark A Lifson, Katina Michael","doi":"10.1109/MPULS.2025.3640837","DOIUrl":"10.1109/MPULS.2025.3640837","url":null,"abstract":"<p><p>Substance use disorders (SUDs) remain a major public health challenge, exacerbated by limited access to care, low treatment engagement, and the disruption of services during the COVID-19 pandemic. Mobile phone applications (MPAs) offer a scalable mechanism for delivering behavioral health interventions; however, existing apps suffer from low engagement, limited methodological rigor, and inflexibility for research and clinical adaptation. This article presents Senyo, a proof-of-concept virtual treatment and research platform designed to support individuals with SUD while enabling systematic evaluation of mobile therapeutic strategies. The platform integrates an extensible mobile application with secure web-based portals for providers and researchers, enabling the delivery of asynchronous cognitive behavioral therapy (CBT) content, activity-based goals, and a token-economy-based contingency management (CM) reward system. Social reinforcement is incorporated through clinician messaging and tele-support, enhancing engagement and adherence. The researcher interface allows for real-time modification of modules, surveys, goals, and incentives without additional app development, facilitating blinded, randomized, and comparative studies within a single platform. The system is designed to be HIPAA compliant and aligned with emerging regulatory frameworks for software as a medical device. This work demonstrates the feasibility of a flexible, research-ready digital therapeutic infrastructure and outlines its potential to improve engagement, support evidence-based care, and advance rigorous evaluation of mobile interventions for SUD and related behavioral health conditions.</p>","PeriodicalId":49065,"journal":{"name":"IEEE Pulse","volume":"16 6","pages":"53-63"},"PeriodicalIF":1.2,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147370573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Nanomedicine Revolution: Tiny Tech With Big Impact on Health Care.","authors":"Nyi Nyi Tun, Bigit Krishna Goswami, Polat Goktas, Nicole Caballero Canchanya","doi":"10.1109/MPULS.2025.3640874","DOIUrl":"10.1109/MPULS.2025.3640874","url":null,"abstract":"<p><p>The nanomedicine revolution represents a paradigm shift in modern health care, leveraging nanoscale materials to achieve unprecedented precision, personalization, and performance in diagnosis and therapy. Emerging from Feynman's foundational vision of nanotechnology, nanomedicine integrates nanoengineering, materials science, and biotechnology to enable targeted drug delivery, advanced imaging, and regenerative applications. Nanoparticles (NPs) function as intelligent carriers that enhance bioavailability and minimize systemic toxicity, while nanoscale contrast agents redefine diagnostic accuracy through enhanced magnetic resonance imaging (MRI), computed tomography (CT), and photoacoustic imaging (PAI). In oncology and infectious diseases, nanomedicine's capacity for selective targeting and antimicrobial innovation is reshaping therapeutic outcomes. The convergence of nanotechnology with artificial intelligence (AI) and machine learning (ML) further facilitates predictive modeling, smart NP design, and real-time clinical decision-making. Despite persistent challenges in safety, scalability, and ethical regulation, nanomedicine is emerging as a cornerstone of precision health care, where \" tiny tech \" delivers an outsized impact on human health. Based on an extensive review of scientific studies published between 1964 and 2025, this article discusses the fundamental principles, biomedical applications, and transformative role of nanomedicine in shaping the next generation of personalized and precision medicine.</p>","PeriodicalId":49065,"journal":{"name":"IEEE Pulse","volume":"16 6","pages":"39-49"},"PeriodicalIF":1.2,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147370559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}