arXiv subjects

Jonathan Chen

Publications and source records attributed to Jonathan Chen.

13 recordsLinked to original sources

arXiv2026

Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence

Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows. Their inherent stochasticity causes minor variations in textual prompts or hyperparameters to yield drastically different outputs often necessitating inefficient, brute-force trial-and-error processes. To address these limitations, we introduce the ``Agentic Self-Improvement" framework, which reframes video synthesis into a closed-loop, goal-directed optimization. Our framework systematically navigates the generation parameter space using a novel two-stage approach. In the first stage, an iterative prompt optimization loop uses a multimodal Large Language Model (mLLM) to refine the input prompt. This refinement implements two automated evaluations: Davidsonian Scene Graph (DSG) queries ensure semantic adherence, and Common Mistake Questions (CMQ) for artifact detection. At the second stage, we use Bayesian optimization to efficiently co-optimize stochastic seeds and CFG scales. This search is guided by a suite of quality metrics, including the novel Video-Text Adherence (VTA) score derived from the DSG and CMQ evaluations. Our framework significantly outperforms unguided search methods: in human preference studies, videos generated via our agentic approach were strongly preferred over baseline outputs, achieving win rates up to 69\%. This work provides a practical and extensible methodology for enhancing the predictability and control of state-of-the-art video generation models, moving the field beyond speculative curiosities toward reliable, production-ready tools.

cs.CV↗

arXiv2026

Multi-Method Validation of Large Language Model Medical Translation Across High- and Low-Resource Languages

Language barriers affect 27.3 million U.S. residents with non-English language preference, yet professional medical translation remains costly and often unavailable. We evaluated four frontier large language models (GPT-5.1, Claude Opus 4.5, Gemini 3 Pro, Kimi K2) translating 22 medical documents into 8 languages spanning high-resource (Spanish, Chinese, Russian, Vietnamese), medium-resource (Korean, Arabic), and low-resource (Tagalog, Haitian Creole) categories using a five-layer validation framework. Across 704 translation pairs, all models achieved high semantic preservation (LaBSE greater than 0.92), with no significant difference between high- and low-resource languages (p = 0.066). Cross-model back-translation confirmed results were not driven by same-model circularity (delta = -0.0009). Inter-model concordance across four independently trained models was high (LaBSE: 0.946), and lexical borrowing analysis showed no correlation between English term retention and fidelity scores in low-resource languages (rho = +0.018, p = 0.82). These converging results suggest frontier LLMs preserve medical meaning across resource levels, with implications for language access in healthcare.

cs.CL↗

arXiv2026

Adoption and Use of LLMs at an Academic Medical Center

While large language models (LLMs) can support clinical documentation needs, standalone tools struggle with "workflow friction" from manual data entry. We developed ChatEHR, a system that enables the use of LLMs with the entire patient timeline spanning several years. ChatEHR enables automations - which are static combinations of prompts and data that perform a fixed task - and interactive use in the electronic health record (EHR) via a user interface (UI). The resulting ability to sift through patient medical records for diverse use-cases such as pre-visit chart review, screening for transfer eligibility, monitoring for surgical site infections, and chart abstraction, redefines LLM use as an institutional capability. This system, accessible after user-training, enables continuous monitoring and evaluation of LLM use. In 1.5 years, we built 7 automations and 1075 users have trained to become routine users of the UI, engaging in 23,000 sessions in the first 3 months of launch. For automations, being model-agnostic and accessing multiple types of data was essential for matching specific clinical or administrative tasks with the most appropriate LLM. Benchmark-based evaluations proved insufficient for monitoring and evaluation of the UI, requiring new methods to monitor performance. Generation of summaries was the most frequent task in the UI, with an estimated 0.73 hallucinations and 1.60 inaccuracies per generation. The resulting mix of cost savings, time savings, and revenue growth required a value assessment framework to prioritize work as well as quantify the impact of using LLMs. Initial estimates are $6M savings in the first year of use, without quantifying the benefit of the better care offered. Such a "build-from-within" strategy provides an opportunity for health systems to maintain agency via a vendor-agnostic, internally governed LLM platform.

cs.CY↗

arXiv2025

Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization

Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck. Current solutions are impractical: fine-tuning requires large annotated datasets scientists often lack, while manual code adaptation costs scientists weeks to months of effort. We consider using AI agents to automate this manual coding, and focus on the open question of optimal agent design for this targeted task. We introduce a systematic evaluation framework for agentic code optimization and use it to study three production-level biomedical imaging pipelines. We demonstrate that a simple agent framework consistently generates adaptation code that outperforms human-expert solutions. Our analysis reveals that common, complex agent architectures are not universally beneficial, leading to a practical roadmap for agent design. We open source our framework and validate our approach by deploying agent-generated functions into a production pipeline, demonstrating a clear pathway for real-world impact.

cs.CV↗

arXiv2025

MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks

While large language models (LLMs) achieve near-perfect scores on medical licensing exams, these evaluations inadequately reflect the complexity and diversity of real-world clinical practice. We introduce MedHELM, an extensible evaluation framework for assessing LLM performance for medical tasks with three key contributions. First, a clinician-validated taxonomy spanning 5 categories, 22 subcategories, and 121 tasks developed with 29 clinicians. Second, a comprehensive benchmark suite comprising 35 benchmarks (17 existing, 18 newly formulated) providing complete coverage of all categories and subcategories in the taxonomy. Third, a systematic comparison of LLMs with improved evaluation methods (using an LLM-jury) and a cost-performance analysis. Evaluation of 9 frontier LLMs, using the 35 benchmarks, revealed significant performance variation. Advanced reasoning models (DeepSeek R1: 66% win-rate; o3-mini: 64% win-rate) demonstrated superior performance, though Claude 3.5 Sonnet achieved comparable results at 40% lower estimated computational cost. On a normalized accuracy scale (0-1), most models performed strongly in Clinical Note Generation (0.73-0.85) and Patient Communication & Education (0.78-0.83), moderately in Medical Research Assistance (0.65-0.75), and generally lower in Clinical Decision Support (0.56-0.72) and Administration & Workflow (0.53-0.63). Our LLM-jury evaluation method achieved good agreement with clinician ratings (ICC = 0.47), surpassing both average clinician-clinician agreement (ICC = 0.43) and automated baselines including ROUGE-L (0.36) and BERTScore-F1 (0.44). Claude 3.5 Sonnet achieved comparable performance to top models at lower estimated cost. These findings highlight the importance of real-world, task-specific evaluation for medical use of LLMs and provides an open source framework to enable this.

cs.CL↗

arXiv2025

Bias-preserving and error-detectable entangling operations in a superconducting dual-rail system

For useful quantum computation, error-corrected machines are required that can dramatically reduce the inevitable errors experienced by physical qubits. While significant progress has been made in approaching and exceeding the surface-code threshold in superconducting platforms, large gains in the logical error rate with increasing system size remain out of reach. This is due both to the large number of required physical qubits and the need to operate far below threshold. Importantly, by exploiting the biases and structure of the physical errors, this threshold can be raised. Erasure qubits achieve this by detecting certain errors at the hardware level. Dual-rail qubits encoded in superconducting cavities are a promising erasure qubit wherein the dominant error, photon loss, can be detected and converted to an erasure. In these approaches, the complete set of operations, including two qubit gates, must be high performance and preserve as much of the desirable hierarchy or bias in the errors as possible. Here, we design and realize a novel two-qubit gate for dual-rail erasure qubits based on superconducting microwave cavities. The gate is high-speed ($\sim$500 ns duration), and yields a residual gate infidelity after error detection below 0.1%. Moreover, we experimentally demonstrate that this gate largely preserves the favorable error structure of idling dual-rail qubits, making it ideal for error correction. We measure low erasure rates of $\sim$0.5% per gate, as well as low and asymmetric dephasing errors that occur at least three times more frequently on control qubits compared to target qubits. Bit-flip errors are practically nonexistent, bounded at the few parts per million level. This error asymmetry has not been well explored but is extremely useful in quantum error correction and flag-qubit contexts, where it can create a faster path to effective error-corrected systems.

quant-ph↗

arXiv2024

Superhuman performance of a large language model on the reasoning tasks of a physician

A seminal paper published by Ledley and Lusted in 1959 introduced complex clinical diagnostic reasoning cases as the gold standard for the evaluation of expert medical computing systems, a standard that has held ever since. Here, we report the results of a physician evaluation of a large language model (LLM) on challenging clinical cases against a baseline of hundreds of physicians. We conduct five experiments to measure clinical reasoning across differential diagnosis generation, display of diagnostic reasoning, triage differential diagnosis, probabilistic reasoning, and management reasoning, all adjudicated by physician experts with validated psychometrics. We then report a real-world study comparing human expert and AI second opinions in randomly-selected patients in the emergency room of a major tertiary academic medical center in Boston, MA. We compared LLMs and board-certified physicians at three predefined diagnostic touchpoints: triage in the emergency room, initial evaluation by a physician, and admission to the hospital or intensive care unit. In all experiments--both vignettes and emergency room second opinions--the LLM displayed superhuman diagnostic and reasoning abilities, as well as continued improvement from prior generations of AI clinical decision support. Our study suggests that LLMs have achieved superhuman performance on general medical diagnostic and management reasoning, fulfilling the vision put forth by Ledley and Lusted, and motivating the urgent need for prospective trials.

cs.AI↗

arXiv2024

Reasoning and Tools for Human-Level Forecasting

Language models (LMs) trained on web-scale datasets are largely successful due to their ability to memorize large amounts of training data, even if only present in a few examples. These capabilities are often desirable in evaluation on tasks such as question answering but raise questions about whether these models can exhibit genuine reasoning or succeed only at mimicking patterns from the training data. This distinction is particularly salient in forecasting tasks, where the answer is not present in the training data, and the model must reason to make logical deductions. We present Reasoning and Tools for Forecasting (RTF), a framework of reasoning-and-acting (ReAct) agents that can dynamically retrieve updated information and run numerical simulation with equipped tools. We evaluate our model with questions from competitive forecasting platforms and demonstrate that our method is competitive with and can outperform human predictions. This suggests that LMs, with the right tools, can indeed think and adapt like humans, offering valuable insights for real-world decision-making.

cs.LG↗

arXiv2024

Constrained Design of a Binary Instrument in a Partially Linear Model

We study the question of how best to assign an encouragement in a randomized encouragement study. In our setting, units arrive with covariates, receive a nudge toward treatment or control, acquire one of those statuses in a way that need not align with the nudge, and finally have a response observed. The nudge can be modeled as a binary instrument if one assumes that it affects the response only via the treatment status. Our goal is to assign the nudge as a function of covariates in a way that best estimates the local average treatment effect (LATE). We assume a partially linear model, wherein the baseline model is non-parametric and the treatment term is linear in the covariates. Under this model, we outline a two-stage procedure to consistently and optimally estimate the LATE. Though the variance of the LATE is intractable, we derive a finite sample approximation and thus a design criterion to minimize. This criterion is convex, allowing for constraints that might arise for budgetary or ethical reasons. We prove conditions under which our solution asymptotically recovers the lowest true variance among all possible nudge propensities. A one-stage version of the algorithm is consistent but not necessarily optimal. We apply our method to a semi-synthetic example involving triage in an emergency department and find significant gains relative to a regression discontinuity design.

stat.ME↗

arXiv2024

Standing on FURM ground -- A framework for evaluating Fair, Useful, and Reliable AI Models in healthcare systems

The impact of using artificial intelligence (AI) to guide patient care or operational processes is an interplay of the AI model's output, the decision-making protocol based on that output, and the capacity of the stakeholders involved to take the necessary subsequent action. Estimating the effects of this interplay before deployment, and studying it in real time afterwards, are essential to bridge the chasm between AI model development and achievable benefit. To accomplish this, the Data Science team at Stanford Health Care has developed a Testing and Evaluation (T&E) mechanism to identify fair, useful and reliable AI models (FURM) by conducting an ethical review to identify potential value mismatches, simulations to estimate usefulness, financial projections to assess sustainability, as well as analyses to determine IT feasibility, design a deployment strategy, and recommend a prospective monitoring and evaluation plan. We report on FURM assessments done to evaluate six AI guided solutions for potential adoption, spanning clinical and operational settings, each with the potential to impact from several dozen to tens of thousands of patients each year. We describe the assessment process, summarize the six assessments, and share our framework to enable others to conduct similar assessments. Of the six solutions we assessed, two have moved into a planning and implementation phase. Our novel contributions - usefulness estimates by simulation, financial projections to quantify sustainability, and a process to do ethical assessments - as well as their underlying methods and open source tools, are available for other healthcare systems to conduct actionable evaluations of candidate AI solutions.

cs.CY↗

arXiv2023

Demonstrating a superconducting dual-rail cavity qubit with erasure-detected logical measurements

A critical challenge in developing scalable error-corrected quantum systems is the accumulation of errors while performing operations and measurements. One promising approach is to design a system where errors can be detected and converted into erasures. Such a system utilizing erasure qubits are known to have relaxed requirements for quantum error correction. A recent proposal aims to do this using a dual-rail encoding with superconducting cavities. However, experimental characterization and demonstration of a dual-rail cavity qubit has not yet been realized. In this work, we implement such a dual-rail cavity qubit; we demonstrate a projective logical measurement with integrated erasure detection and use it to measure dual-rail qubit idling errors. We measure logical state preparation and measurement errors at the $0.01\%$-level and detect over $99\%$ of cavity decay events as erasures. We use the precision of this new measurement protocol to distinguish different types of errors in this system, finding that while decay errors occur with probability $\sim 0.2\%$ per microsecond, phase errors occur 6 times less frequently and bit flips occur at least 140 times less frequently. These findings represent the first confirmation of the expected error hierarchy necessary to concatenate dual-rail erasure qubits into a highly efficient erasure code.

quant-ph↗

arXiv2019

Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators

Machine learning advances have afforded an increase in algorithms capable of creating art, music, stories, games, and more. However, it is not yet well-understood how machine learning algorithms might best collaborate with people to support creative expression. To investigate how practicing designers perceive the role of AI in the creative process, we developed a game level design tool for Super Mario Bros.-style games with a built-in AI level designer. In this paper we discuss our design of the Morai Maker intelligent tool through two mixed-methods studies with a total of over one-hundred participants. Our findings are as follows: (1) level designers vary in their desired interactions with, and role of, the AI, (2) the AI prompted the level designers to alter their design practices, and (3) the level designers perceived the AI as having potential value in their design practice, varying based on their desired role for the AI.

cs.HC↗

arXiv2018

Explainable PCGML via Game Design Patterns

Procedural content generation via Machine Learning (PCGML) is the umbrella term for approaches that generate content for games via machine learning. One of the benefits of PCGML is that, unlike search or grammar-based PCG, it does not require hand authoring of initial content or rules. Instead, PCGML relies on existing content and black box models, which can be difficult to tune or tweak without expert knowledge. This is especially problematic when a human designer needs to understand how to manipulate their data or models to achieve desired results. We present an approach to Explainable PCGML via Design Patterns in which the design patterns act as a vocabulary and mode of interaction between user and model. We demonstrate that our technique outperforms non-explainable versions of our system in interactions with five expert designers, four of whom lack any machine learning expertise.

cs.AI↗