Searcharxiv⌕ Search

arXiv subjects

Matthew Turk

Publications and source records attributed to Matthew Turk.

At least 19 recordsLinked to original sources
arXiv2025

Spezi Data Pipeline: Streamlining FHIR-based Interoperable Digital Health Data Workflows

The increasing adoption of digital health technologies has amplified the need for robust, interoperable solutions to manage complex healthcare data. We present the Spezi Data Pipeline, an open-source Python toolkit designed to streamline the analysis of digital health data, from secure access and retrieval to processing, visualization, and export. The Pipeline is integrated into the larger Stanford Spezi open-source ecosystem for developing research and translational digital health software systems. Leveraging HL7 FHIR-based data representations, the pipeline enables standardized handling of diverse data types--including sensor-derived observations, ECG recordings, and clinical questionnaires--across research and clinical environments. We detail the modular system architecture and demonstrate its application using real-world data from the PAWS at Stanford University, in which the pipeline facilitated efficient extraction, transformation, and clinician-driven review of Apple Watch ECG data, supporting annotation and comparative analysis alongside traditional monitors. By reducing the need for bespoke development and enhancing workflow efficiency, the Spezi Data Pipeline advances the scalability and interoperability of digital health research, ultimately supporting improved care delivery and patient outcomes.

cs.DB↗
arXiv2025

Now More Than Ever, Foundational AI Research and Infrastructure Depends on the Federal Government

Leadership in the field of AI is vital for our nation's economy and security. Maintaining this leadership requires investments by the federal government. The federal investment in foundation AI research is essential for U.S. leadership in the field. Providing accessible AI infrastructure will benefit everyone. Now is the time to increase the federal support, which will be complementary to, and help drive, the nation's high-tech industry investments.

cs.CY↗
arXiv2025

Concerning the Responsible Use of AI in the US Criminal Justice System

Artificial intelligence (AI) is increasingly being adopted in most industries, and for applications such as note taking and checking grammar, there is typically not a cause for concern. However, when constitutional rights are involved, as in the justice system, transparency is paramount. While AI can assist in areas such as risk assessment and forensic evidence generation, its "black box" nature raises significant questions about how decisions are made and whether they can be contested. This paper explores the implications of AI in the justice system, emphasizing the need for transparency in AI decision-making processes to uphold constitutional rights and ensure procedural fairness. The piece advocates for clear explanations of AI's data, logic, and limitations, and calls for periodic audits to address bias and maintain accountability in AI systems.

cs.CY↗
arXiv2025

Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models

The biases exhibited by text-to-image (TTI) models are often treated as independent, though in reality, they may be deeply interrelated. Addressing bias along one dimension - such as ethnicity or age - can inadvertently affect another, like gender, either mitigating or exacerbating existing disparities. Understanding these interdependencies is crucial for designing fairer generative models, yet measuring such effects quantitatively remains a challenge. To address this, we introduce BiasConnect, a novel tool for analyzing and quantifying bias interactions in TTI models. BiasConnect uses counterfactual interventions along different bias axes to reveal the underlying structure of these interactions and estimates the effect of mitigating one bias axis on another. These estimates show strong correlation (+0.65) with observed post-mitigation outcomes. Building on BiasConnect, we propose InterMit, an intersectional bias mitigation algorithm guided by user-defined target distributions and priority weights. InterMit achieves lower bias (0.33 vs. 0.52) with fewer mitigation steps (2.38 vs. 3.15 average steps), and yields superior image quality compared to traditional techniques. Although our implementation is training-free, InterMit is modular and can be integrated with many existing debiasing approaches for TTI models, making it a flexible and extensible solution.

cs.CV↗
arXiv2024

Addressing the Unforeseen Harms of Technology CCC Whitepaper

Recent years have seen increased awareness of the potential significant impacts of computing technologies, both positive and negative. This whitepaper explores how to address possible harmful consequences of computing technologies that might be difficult to anticipate, and thereby mitigate or address. It starts from the assumption that very few harms due to technology are intentional or deliberate; rather, the vast majority result from failure to recognize and respond to them prior to deployment. Nonetheless, there are concrete steps that can be taken to address the difficult problem of anticipating and responding to potential harms from new technologies.

cs.CY↗
arXiv2024

Utilizing Adversarial Examples for Bias Mitigation and Accuracy Enhancement

We propose a novel approach to mitigate biases in computer vision models by utilizing counterfactual generation and fine-tuning. While counterfactuals have been used to analyze and address biases in DNN models, the counterfactuals themselves are often generated from biased generative models, which can introduce additional biases or spurious correlations. To address this issue, we propose using adversarial images, that is images that deceive a deep neural network but not humans, as counterfactuals for fair model training. Our approach leverages a curriculum learning framework combined with a fine-grained adversarial loss to fine-tune the model using adversarial examples. By incorporating adversarial images into the training data, we aim to prevent biases from propagating through the pipeline. We validate our approach through both qualitative and quantitative assessments, demonstrating improved bias mitigation and accuracy compared to existing methods. Qualitatively, our results indicate that post-training, the decisions made by the model are less dependent on the sensitive attribute and our model better disentangles the relationship between sensitive attributes and classification variables.

cs.CV↗
arXiv2023

TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models

Text-to-Image (TTI) generative models have shown great progress in the past few years in terms of their ability to generate complex and high-quality imagery. At the same time, these models have been shown to suffer from harmful biases, including exaggerated societal biases (e.g., gender, ethnicity), as well as incidental correlations that limit such a model's ability to generate more diverse imagery. In this paper, we propose a general approach to study and quantify a broad spectrum of biases, for any TTI model and for any prompt, using counterfactual reasoning. Unlike other works that evaluate generated images on a predefined set of bias axes, our approach automatically identifies potential biases that might be relevant to the given prompt, and measures those biases. In addition, we complement quantitative scores with post-hoc explanations in terms of semantic concepts in the images generated. We show that our method is uniquely capable of explaining complex multi-dimensional biases through semantic concepts, as well as the intersectionality between different biases for any given prompt. We perform extensive user studies to illustrate that the results of our method and analysis are consistent with human judgements.

cs.CV↗
arXiv2022

Reduced Order Model for Chemical Kinetics: A case study with Primordial Chemical Network

Chemical kinetics plays an important role in governing the thermal evolution in reactive flows problems. The possible interactions between chemical species increase drastically with the number of species considered in the system. Various ways have been proposed before to simplify chemical networks with an aim to reduce the computational complexity of the chemical network. These techniques oftentimes require domain-knowledge experts to handcraftedly identify important reaction pathways and possible simplifications. Here, we propose a combination of autoencoder and neural ordinary differential equation to model the temporal evolution of chemical kinetics in a reduced subspace. We demonstrated that our model has achieved a close-to 10-fold speed-up compared to commonly used astro-chemistry solver for a 9-species primordial network, while maintaining 1 percent accuracy across a wide-range of density and temperature.

astro-ph.IM↗
arXiv2021

Sparse Fusion for Multimodal Transformers

Multimodal classification is a core task in human-centric machine learning. We observe that information is highly complementary across modalities, thus unimodal information can be drastically sparsified prior to multimodal fusion without loss of accuracy. To this end, we present Sparse Fusion Transformers (SFT), a novel multimodal fusion method for transformers that performs comparably to existing state-of-the-art methods while having greatly reduced memory footprint and computation cost. Key to our idea is a sparse-pooling block that reduces unimodal token sets prior to cross-modality modeling. Evaluations are conducted on multiple multimodal benchmark datasets for a wide range of classification tasks. State-of-the-art performance is obtained on multiple benchmarks under similar experiment conditions, while reporting up to six-fold reduction in computational cost and memory requirements. Extensive ablation studies showcase our benefits of combining sparsification and multimodal learning over naive approaches. This paves the way for enabling multimodal learning on low-resource devices.

cs.CV↗
arXiv2021

One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification

Real-world classification tasks are frequently required to work in an open-set setting. This is especially challenging for few-shot learning problems due to the small sample size for each known category, which prevents existing open-set methods from working effectively; however, most multiclass few-shot methods are limited to closed-set scenarios. In this work, we address the problem of few-shot open-set classification by first proposing methods for few-shot one-class classification and then extending them to few-shot multiclass open-set classification. We introduce two independent few-shot one-class classification methods: Meta Binary Cross-Entropy (Meta-BCE), which learns a separate feature representation for one-class classification, and One-Class Meta-Learning (OCML), which learns to generate one-class classifiers given standard multiclass feature representation. Both methods can augment any existing few-shot learning method without requiring retraining to work in a few-shot multiclass open-set setting without degrading its closed-set performance. We demonstrate the benefits and drawbacks of both methods in different problem settings and evaluate them on three standard benchmark datasets, miniImageNet, tieredImageNet, and Caltech-UCSD-Birds-200-2011, where they surpass the state-of-the-art methods in the few-shot multiclass open-set and few-shot one-class tasks.

cs.CV↗
arXiv2021

The AGORA High-resolution Galaxy Simulations Comparison Project. III: Cosmological zoom-in simulation of a Milky Way-mass halo

We present a suite of high-resolution cosmological zoom-in simulations to $z=4$ of a $10^{12}\,{\rm M}_{\odot}$ halo at $z=0$, obtained using seven contemporary astrophysical simulation codes widely used in the numerical galaxy formation community. Physics prescriptions for gas cooling, heating, and star formation, are similar to the ones used in our previous {\it AGORA} disk comparison but now account for the effects of cosmological processes. In this work, we introduce the most careful comparison yet of galaxy formation simulations run by different code groups, together with a series of four calibration steps each of which is designed to reduce the number of tunable simulation parameters adopted in the final run. After all the participating code groups successfully completed the calibration steps, we reach a suite of cosmological simulations with similar mass assembly histories down to $z=4$. With numerical accuracy that resolves the internal structure of a target halo, we find that the codes overall agree well with one another in e.g., gas and stellar properties, but also show differences in e.g., circumgalactic medium properties. We argue that, if adequately tested in accordance with our proposed calibration steps and common parameters, the results of high-resolution cosmological zoom-in simulations can be robust and reproducible. New code groups are invited to join this comparison by generating equivalent models by adopting the common initial conditions, the common easy-to-implement physics package, and the proposed calibration steps. Further analyses of the simulations presented here will be in forthcoming reports from our Collaboration.

astro-ph.GA↗
arXiv2019

Large Scale Dynamo in a Primordial Accretion Flow -- An Interpretation from Hydrodynamic Simulation

Without an existing large scale coherent magnetic field in the early Universe, Population III (PopIII) stars would likely rotate at or near break-up speed. In this work, focusing on the accretion phase of PopIII stars, we investigate the possibility of generating a coherent magnetic field through large scale dynamo processes, as well as the corresponding field saturation level. Using results from hydrodynamic simulations, we demonstrate that primordial accretion disks are turbulent with a Shakura-Sunyaev disk parameter $\alpha_{ss} \gtrsim 10^{-3}$, and evidence helical turbulence with a dynamo number $\vert D_{\alpha \Omega} \vert \gg 10$. The presence of helical turbulence at these levels allows large scale dynamo modes to grow, and the saturation level is determined by the amount of net helicity remaining in the dynamo-active regions (a.k.a. the quenching problem). %We demonstrate that the magnetic field can reach approximate equipartition, with $B/B_{\rm eq} \sim 3$, indicating that the dynamo quenching problem could be alleviated through an accretion flow. We demonstrate that, if the accretion could successfully alleviate the quenching problem, the magnetic field can reach approximate equipartition with $B/B_{\rm eq} \sim 3$.

astro-ph.GA↗
arXiv2019

Fragmentation in a Primordial Accretion Flow

Under rapid cooling from molecular hydrogen, the accretion disks around Population III (PopIII) stars are believed to fragment, resulting in multiple accreting cores. In this paper, we build a theoretical framework for calculating the optical depth of H$_2$ ro-vibrational line cooling based on the vertical structure in these accretion disks. Applying this physically motivated prescription for the optical depth, we find that cooling in the inner disk with $r \lesssim 10 {\rm\ AU}$ is attenuated significantly as a result of high surface density; $PdV$ heating becomes more efficient than cooling, which prevents fragmentation in the inner disk. Despite this, cooling becomes dynamically important in the outer disk, favoring fragmentation. We argue that most of the resultant fragments are initially at the outer disk, and that any surviving fragment has to migrate slower than the disk-scale photo-evaporation process. Since type I migration is fast, migration slows down as a result of gap-opening in the disk structure. Two possible processes for gap-opening are studied: (1) through a massive, densely-cored ($\rho \gtrsim 10^{-8} {\rm\ g\ cm^{-3}}$) clump able to radiate away the excess gravitational potential energy, and (2) through a fast-growing central star, with $\dot{M} \gtrsim 2 \times 10^{-3} \, M_\odot {\rm\ yr^{-1}}$, whose gravity dominates the star-disk system and favors gap opening.

astro-ph.GA↗
arXiv2019

Theory-Software Translation: Research Challenges and Future Directions

The Theory-Software Translation Workshop, held in New Orleans in February 2019, explored in depth the process of both instantiating theory in software - for example, implementing a mathematical model in code as part of a simulation - and using the outputs of software - such as the behavior of a simulation - to advance knowledge. As computation within research is now ubiquitous, the workshop provided a timely opportunity to reflect on the particular challenges of research software engineering - the process of developing and maintaining software for scientific discovery. In addition to the general challenges common to all software development projects, research software additionally must represent, manipulate, and provide data for complex theoretical constructs. Ensuring this process is robust is essential to maintaining the integrity of the science resulting from it, and the workshop highlighted a number of areas where the current approach to research software engineering would benefit from an evidence base that could be used to inform best practice. The workshop brought together expert research software engineers and academics to discuss the challenges of Theory-Software Translation over a two-day period. This report provides an overview of the workshop activities, and a synthesises of the discussion that was recorded. The body of the report presents a thematic analysis of the challenges of Theory-Software Translation as identified by workshop participants, summarises these into a set of research areas, and provides recommendations for the future direction of this work.

cs.SE↗
arXiv2019

What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog

The ability to engage in goal-oriented conversations has allowed humans to gain knowledge, reduce uncertainty, and perform tasks more efficiently. Artificial agents, however, are still far behind humans in having goal-driven conversations. In this work, we focus on the task of goal-oriented visual dialogue, aiming to automatically generate a series of questions about an image with a single objective. This task is challenging since these questions must not only be consistent with a strategy to achieve a goal, but also consider the contextual information in the image. We propose an end-to-end goal-oriented visual dialogue system, that combines reinforcement learning with regularized information gain. Unlike previous approaches that have been proposed for the task, our work is motivated by the Rational Speech Act framework, which models the process of human inquiry to reach a goal. We test the two versions of our model on the GuessWhat?! dataset, obtaining significant results that outperform the current state-of-the-art models in the task of generating questions to find an undisclosed object in an image.

cs.CL↗
arXiv2019

Astro2020 APC White Paper: Elevating the Role of Software as a Product of the Research Enterprise

Software is a critical part of modern research, and yet there are insufficient mechanisms in the scholarly ecosystem to acknowledge, cite, and measure the impact of research software. The majority of academic fields rely on a one-dimensional credit model whereby academic articles (and their associated citations) are the dominant factor in the success of a researcher's career. In the petabyte era of astronomical science, citing software and measuring its impact enables academia to retain and reward researchers that make significant software contributions. These highly skilled researchers must be retained to maximize the scientific return from petabyte-scale datasets. Evolving beyond the one-dimensional credit model requires overcoming several key challenges, including the current scholarly ecosystem and scientific culture issues. This white paper will present these challenges and suggest practical solutions for elevating the role of software as a product of the research enterprise.

astro-ph.IM↗
arXiv2017

ANSAC: Adaptive Non-minimal Sample and Consensus

While RANSAC-based methods are robust to incorrect image correspondences (outliers), their hypothesis generators are not robust to correct image correspondences (inliers) with positional error (noise). This slows down their convergence because hypotheses drawn from a minimal set of noisy inliers can deviate significantly from the optimal model. This work addresses this problem by introducing ANSAC, a RANSAC-based estimator that accounts for noise by adaptively using more than the minimal number of correspondences required to generate a hypothesis. ANSAC estimates the inlier ratio (the fraction of correct correspondences) of several ranked subsets of candidate correspondences and generates hypotheses from them. Its hypothesis-generation mechanism prioritizes the use of subsets with high inlier ratio to generate high-quality hypotheses. ANSAC uses an early termination criterion that keeps track of the inlier ratio history and terminates when it has not changed significantly for a period of time. The experiments show that ANSAC finds good homography and fundamental matrix estimates in a few iterations, consistently outperforming state-of-the-art methods.

cs.CV↗