arXiv subjects

Zhe He

Publications and source records attributed to Zhe He.

At least 19 recordsLinked to original sources

arXiv2026

Investigating Memory in Model-Free RL with POPGym Arcade

How should we analyze memory in deep RL? We introduce tools for analyzing policies under partial observability and revealing how agents use memory to make decisions. To utilize these tools, we present POPGym Arcade, a collection of Atari-inspired, hardware-accelerated environments sharing a single observation and action space. Each environment provides fully and partially observable variants, enabling counterfactual studies on observability. We find that controlled studies are necessary for fair comparisons and identify a pathology where value functions smear credit over irrelevant history. Using this pathology, we demonstrate how out-of-distribution scenarios can contaminate memory, perturbing the policy far into the future. Our code is available at https://github.com/bolt-research/popgym-arcade.

cs.LG↗

arXiv2026

SynEHR: Joint Modeling Inter-visit Temporal Evolution and Intra-visit Clinical Structure for Longitudinal EHR Synthesis

Longitudinal electronic health records (EHRs) document patients' sequences of clinical visits over time, preserving the temporal evolution of disease progression and care delivery. However, real longitudinal EHRs are difficult to access because they contain large amounts of fine-grained, patient-specific information. Synthetic EHR generation therefore provides a valuable approach for preserving the statistical patterns and clinical structure of patient visit trajectories, enabling broader modeling and analysis when real records are limited. Although recent generative models have made progress in producing future visit sequences, they remain limited in explicitly integrating inter-visit irregular temporal evolution and intra-visit clinical event structures in EHRs, leading to clinically inconsistent and temporally unrealistic visit sequences. In this work, we propose SynEHR, a lightweight adaptive LLM-based framework for longitudinal EHR synthesis. There are two novel designs in SynEHR, i.e., a Temporal State Conditioning Module captures irregular temporal states across visits and a Temporal-Relational Adaptation Module combines these states with patient history to dynamically construct patient-specific relational representations. SynEHR then builds on a parameter-efficient LoRA-adapted language-model generator with next-visit generation capability to train the two modules for temporally and clinically informed generation. Extensive experiments on real-world EHR datasets across fidelity, privacy, and downstream utility evaluations demonstrate that SynEHR outperforms state-of-the-art models by generating more clinically coherent and temporally faithful longitudinal EHR data.

cs.LG↗

arXiv2026

Quantum Imaging via Kurtosis-Difference Weighted Covariance on 2D Camera

Camera-based quantum imaging detects spatially correlated photon pairs from spontaneous parametric down-conversion (SPDC). Conventional covariance methods typically require tens of thousands of frames to extract weak correlations from noise. While thick crystals can increase photon flux, they generate photon pairs from multiple emission positions within the crystal, producing multiple correlation centers with complex pairing geometries. In addition, conventional covariance methods assume a single pre-selected correlation center and cannot fully exploit these distributed correlations. We demonstrate that kurtosis difference, a fourth-order statistic measuring tail similarity, effectively discriminates correlated pixel pairs even when correlation coefficients remain low. Weighting covariance by an exponential function of absolute kurtosis difference can select symmetric pixels while preserving true coincidences. This kurtosis weighting automatically identifies correlated pairs within a broad search region and accommodates multiple pairing geometries without requiring precise correlation center calibration. At 5000 frames, our method yields a contrast-to-noise ratio (CNR) exceeding 7, whereas standard covariance remains below 2. Compared with standard covariance, the method reduces the acquisition time by 40-fold and could enable practical quantum imaging in sparse correlated-photon regimes.

quant-ph↗

arXiv2026

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

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.

cs.AI↗

arXiv2026

HiSync: Spatio-Temporally Aligning Hand Motion from Wearable IMU and On-Robot Camera for Command Source Identification in Long-Range HRI

Long-range Human-Robot Interaction (HRI) remains underexplored. Within it, Command Source Identification (CSI) - determining who issued a command - is especially challenging due to multi-user and distance-induced sensor ambiguity. We introduce HiSync, an optical-inertial fusion framework that treats hand motion as binding cues by aligning robot-mounted camera optical flow with hand-worn IMU signals. We first elicit a user-defined (N=12) gesture set and collect a multimodal command gesture dataset (N=38) in long-range multi-user HRI scenarios. Next, HiSync extracts frequency-domain hand motion features from both camera and IMU data, and a learned CSINet denoises IMU readings, temporally aligns modalities, and performs distance-aware multi-window fusion to compute cross-modal similarity of subtle, natural gestures, enabling robust CSI. In three-person scenes up to 34m, HiSync achieves 92.32% CSI accuracy, outperforming the prior SOTA by 48.44%. HiSync is also validated on real-robot deployment. By making CSI reliable and natural, HiSync provides a practical primitive and design guidance for public-space HRI. https://github.com/OctopusWen/HiSync

cs.HC↗

arXiv2026

A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectives

Synthetic data generation using large language models (LLMs) demonstrates substantial promise in addressing biomedical data challenges and shows increasing adoption in biomedical research. This study systematically reviews recent advances in synthetic data generation for biomedical applications and clinical research, focusing on how LLMs address data scarcity, utility, and quality issues with different modalities. We conducted a scoping review following PRISMA-ScR guidelines and searched literature published between 2020 and 2025 through PubMed, ACM, Web of Science, and Google Scholar. A total of 59 studies were included based on relevance to synthetic data generation in biomedical contexts. Among the reviewed studies, the predominant data modalities were unstructured texts (78.0\%), tabular data (13.6\%), and multimodal sources (8.4\%). Common generation methods included LLM prompting (74.6\%), fine-tuning (20.3\%), and specialized models (5.1\%). Evaluations were heterogeneous: intrinsic metrics (27.1\%), human-in-the-loop assessments (44.1\%), and LLM-based evaluations (13.6\%). However, limitations and key barriers persist in data modalities, domain utility, resource and model accessibility, and standardized evaluation protocols. Future efforts may focus on developing standardized, transparent evaluation frameworks and expanding accessibility to support effective applications in biomedical research.

cs.CL↗

arXiv2025

Utilizing Large Language Models for Zero-Shot Medical Ontology Extension from Clinical Notes

Integrating novel medical concepts and relationships into existing ontologies can significantly enhance their coverage and utility for both biomedical research and clinical applications. Clinical notes, as unstructured documents rich with detailed patient observations, offer valuable context-specific insights and represent a promising yet underutilized source for ontology extension. Despite this potential, directly leveraging clinical notes for ontology extension remains largely unexplored. To address this gap, we propose CLOZE, a novel framework that uses large language models (LLMs) to automatically extract medical entities from clinical notes and integrate them into hierarchical medical ontologies. By capitalizing on the strong language understanding and extensive biomedical knowledge of pre-trained LLMs, CLOZE effectively identifies disease-related concepts and captures complex hierarchical relationships. The zero-shot framework requires no additional training or labeled data, making it a cost-efficient solution. Furthermore, CLOZE ensures patient privacy through automated removal of protected health information (PHI). Experimental results demonstrate that CLOZE provides an accurate, scalable, and privacy-preserving ontology extension framework, with strong potential to support a wide range of downstream applications in biomedical research and clinical informatics.

cs.AI↗

arXiv2025

Evaluation of Causal Reasoning for Large Language Models in Contextualized Clinical Scenarios of Laboratory Test Interpretation

This study evaluates causal reasoning in large language models (LLMs) using 99 clinically grounded laboratory test scenarios aligned with Pearl's Ladder of Causation: association, intervention, and counterfactual reasoning. We examined common laboratory tests such as hemoglobin A1c, creatinine, and vitamin D, and paired them with relevant causal factors including age, gender, obesity, and smoking. Two LLMs - GPT-o1 and Llama-3.2-8b-instruct - were tested, with responses evaluated by four medically trained human experts. GPT-o1 demonstrated stronger discriminative performance (AUROC overall = 0.80 +/- 0.12) compared to Llama-3.2-8b-instruct (0.73 +/- 0.15), with higher scores across association (0.75 vs 0.72), intervention (0.84 vs 0.70), and counterfactual reasoning (0.84 vs 0.69). Sensitivity (0.90 vs 0.84) and specificity (0.93 vs 0.80) were also greater for GPT-o1, with reasoning ratings showing similar trends. Both models performed best on intervention questions and worst on counterfactuals, particularly in altered outcome scenarios. These findings suggest GPT-o1 provides more consistent causal reasoning, but refinement is required before adoption in high-stakes clinical applications.

cs.AI↗

arXiv2025

τ-Ring: A Smart Ring Platform for Multimodal Physiological and Behavioral Sensing

Smart rings have emerged as uniquely convenient devices for continuous physiological and behavioral sensing, offering unobtrusive, constant access to metrics such as heart rate, motion, and skin temperature. Yet most commercial solutions remain proprietary, hindering reproducibility and slowing innovation in wearable research. We introduce τ-Ring, a commercial-ready platform that bridges this gap through: (i) accessible hardware combining time-synchronized multi-channel PPG, 6-axis IMU, temperature sensing, NFC, and on-board storage; (ii) adjustable firmware that lets researchers rapidly reconfigure sampling rates, power modes, and wireless protocols; and (iii) a fully open-source Android software suite that supports both real-time streaming and 8-hour offline logging. Together, these features enable out-of-the-box, reproducible acquisition of rich physiological and behavioral datasets, accelerating prototyping and standardizing experimentation. We validate the platform with demonstration studies in heart-rate monitoring and ring-based handwriting recognition. Source code is available at GitHub: https://github.com/thuhci/OpenRing.

cs.CE↗

arXiv2025

Heisenberg Scaling Quantum Microscopy: Experiment and Theory

Entangled biphoton sources exhibit nonclassical characteristics and have been applied to imaging techniques such as ghost imaging, quantum holography, and quantum optical coherence tomography. The development of wide-field quantum imaging to date has been hindered by low spatial resolutions, speeds, and contrast-to-noise ratios (CNRs). Here, we present quantum microscopy by coincidence (QMC) with balanced pathlengths, which enables super-resolution imaging at the Heisenberg limit with substantially higher speeds and CNRs than existing wide-field quantum imaging methods. QMC benefits from a configuration with balanced pathlengths, where a pair of entangled photons traversing symmetric paths with balanced optical pathlengths in two arms behave like a single photon with half the wavelength, leading to 2-fold resolution improvement. Concurrently, QMC resists stray light up to 155 times stronger than classical signals. The low intensity and entanglement features of biphotons in QMC promise nondestructive bioimaging. QMC advances quantum imaging to the microscopic level with significant improvements in speed and CNR toward bioimaging of cancer cells. We experimentally and theoretically prove that the configuration with balanced pathlengths illuminates an avenue for quantum-enhanced coincidence imaging at the Heisenberg limit.

quant-ph↗

arXiv2025

HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class

Large language models (LLMs) have shown remarkable progress in mathematical problem-solving, but evaluation has largely focused on problems that have exact analytical solutions or involve formal proofs, often overlooking approximation-based problems ubiquitous in applied science and engineering. To fill this gap, we build on prior work and present HARDMath2, a dataset of 211 original problems covering the core topics in an introductory graduate applied math class, including boundary-layer analysis, WKB methods, asymptotic solutions of nonlinear partial differential equations, and the asymptotics of oscillatory integrals. This dataset was designed and verified by the students and instructors of a core graduate applied mathematics course at Harvard. We build the dataset through a novel collaborative environment that challenges students to write and refine difficult problems consistent with the class syllabus, peer-validate solutions, test different models, and automatically check LLM-generated solutions against their own answers and numerical ground truths. Evaluation results show that leading frontier models still struggle with many of the problems in the dataset, highlighting a gap in the mathematical reasoning skills of current LLMs. Importantly, students identified strategies to create increasingly difficult problems by interacting with the models and exploiting common failure modes. This back-and-forth with the models not only resulted in a richer and more challenging benchmark but also led to qualitative improvements in the students' understanding of the course material, which is increasingly important as we enter an age where state-of-the-art language models can solve many challenging problems across a wide domain of fields.

cs.LG↗

arXiv2025

Tip-Enhanced Raman Spectroscopy of Cell Wall Heterogeneity for Aspergillus Fumigatus

Tip-enhanced Raman spectroscopy (TERS) enables nanoscale chemical mapping of biological structures, providing high-resolution, high-signal-to-noise ratio imaging into molecular distribution and interactions beyond the capabilities of conventional Raman imaging. However, challenges such as the deformation of fragile biological cells and the complexity of signal interpretation would increase the difficulty in investigating biological samples with TERS. Here, we demonstrate using TERS to investigate the cell wall heterogeneity of Aspergillus fumigatus spores. Using TERS imaging and spectral analysis, we map the chemical components including melanin within the fungal cell wall. The results reveal distinct spectral features associated with polysaccharides, lipids, and proteins. Furthermore, by comparing the wild-type and albino mutant spores, we illuminate the biochemical characteristics of Dihydroxynaphthalene melanin (DHN-melanin) in the fungal cell wall.

physics.optics↗

arXiv2025

Lab-AI: Using Retrieval Augmentation to Enhance Language Models for Personalized Lab Test Interpretation in Clinical Medicine

Accurate interpretation of lab results is crucial in clinical medicine, yet most patient portals use universal normal ranges, ignoring conditional factors like age and gender. This study introduces Lab-AI, an interactive system that offers personalized normal ranges using retrieval-augmented generation (RAG) from credible health sources. Lab-AI has two modules: factor retrieval and normal range retrieval. We tested these on 122 lab tests: 40 with conditional factors and 82 without. For tests with factors, normal ranges depend on patient-specific information. Our results show GPT-4-turbo with RAG achieved a 0.948 F1 score for factor retrieval and 0.995 accuracy for normal range retrieval. GPT-4-turbo with RAG outperformed the best non-RAG system by 33.5% in factor retrieval and showed 132% and 100% improvements in question-level and lab-level performance, respectively, for normal range retrieval. These findings highlight Lab-AI's potential to enhance patient understanding of lab results.

cs.CL↗

arXiv2025

Computing with Smart Rings: A Systematic Literature Review

A smart ring is a wearable electronic device in the form of a ring that incorporates diverse sensors and computing technologies to perform a variety of functions. Designed for use with fingers, smart rings are capable of sensing more subtle and abundant hand movements, thus making them a good platform for interaction. Meanwhile, fingers are abundant with blood vessels and nerve endings and accustomed to wearing rings, providing an ideal site for continuous health monitoring through smart rings, which combine comfort with the ability to capture vital biometric data, making them suitable for all-day wear. We collected in total of 206 smart ring-related publications and conducted a systematic literature review. We provide a taxonomy regarding the sensing and feedback modalities, applications, and phenomena. We review and categorize these literatures into four main areas: (1) interaction - input, (2) interaction - output, (3) passive sensing - in body feature, (4) passive sensing - out body activity. This comprehensive review highlights the current advancements within the field of smart ring and identifies potential areas for future research.

cs.HC↗

arXiv2024

Evaluating the Impact of Lab Test Results on Large Language Models Generated Differential Diagnoses from Clinical Case Vignettes

Differential diagnosis is crucial for medicine as it helps healthcare providers systematically distinguish between conditions that share similar symptoms. This study assesses the impact of lab test results on differential diagnoses (DDx) made by large language models (LLMs). Clinical vignettes from 50 case reports from PubMed Central were created incorporating patient demographics, symptoms, and lab results. Five LLMs GPT-4, GPT-3.5, Llama-2-70b, Claude-2, and Mixtral-8x7B were tested to generate Top 10, Top 5, and Top 1 DDx with and without lab data. A comprehensive evaluation involving GPT-4, a knowledge graph, and clinicians was conducted. GPT-4 performed best, achieving 55% accuracy for Top 1 diagnoses and 60% for Top 10 with lab data, with lenient accuracy up to 80%. Lab results significantly improved accuracy, with GPT-4 and Mixtral excelling, though exact match rates were low. Lab tests, including liver function, metabolic/toxicology panels, and serology/immune tests, were generally interpreted correctly by LLMs for differential diagnosis.

cs.CL↗

arXiv2024

Quantum mechanical modeling of the multi-stage Stern$\unicode{x2013}$Gerlach experiment conducted by Frisch and Segrè

The multi-stage Stern$\unicode{x2013}$Gerlach experiment conducted by Frisch and Segrè includes two cascaded quantum measurements with a nonadiabatic flipper in between. The Frisch and Segrè experiment has been modeled analytically by Majorana without the nuclear effect and subsequently revised by Rabi with the hyperfine interaction. However, the theoretical predictions do not match the experimental observation accurately. Here, we numerically solve the standard quantum mechanical model, via the von Neumann equation, including the hyperfine interaction for the time evolution of the spin. Thus far, the coefficients of determination from the standard quantum mechanical model without using free parameters are still low, indicating a mismatch between the theory and the experiment. Non-standard variants that improve the match are explored for discussion.

quant-ph↗

arXiv2024

Time Matters: Examine Temporal Effects on Biomedical Language Models

Time roots in applying language models for biomedical applications: models are trained on historical data and will be deployed for new or future data, which may vary from training data. While increasing biomedical tasks have employed state-of-the-art language models, there are very few studies have examined temporal effects on biomedical models when data usually shifts across development and deployment. This study fills the gap by statistically probing relations between language model performance and data shifts across three biomedical tasks. We deploy diverse metrics to evaluate model performance, distance methods to measure data drifts, and statistical methods to quantify temporal effects on biomedical language models. Our study shows that time matters for deploying biomedical language models, while the degree of performance degradation varies by biomedical tasks and statistical quantification approaches. We believe this study can establish a solid benchmark to evaluate and assess temporal effects on deploying biomedical language models.

cs.CL↗

arXiv2024

Capturing dynamics and thermodynamics of a three-level quantum heat engine via programmable quantum circuits

This research employs the Kraus representation and Sz.-Nagy dilation theorem to model a three-level quantum heat on quantum circuits, investigating its dynamic evolution and thermodynamic performance. The feasibility of the dynamic model is validated by tracking the changes of population. On the basis of reinforcement learning algorithm, the optimal cycle of the quantum heat engine for maximal average power is proposed and verified by the thermodynamic model. The stability of quantum circuit simulations is scrutinized through a comparative analysis of theoretical and simulated results, predicated on an orthogonal test. These results affirm the practicality of simulating quantum heat engines on quantum circuits, offering potential for substantially curtailing the experimental expenses associated with the construction of such engines.

quant-ph↗