arXiv subjects

Eric C. Larson

Publications and source records attributed to Eric C. Larson.

At least 19 recordsLinked to original sources

arXiv2026

Multimodal Routing for Interpretable, Robust, and Auditable Clinical Prediction

Electronic health record (EHR) data are inherently multimodal, and leveraging multiple modalities can improve predictive performance. However, most existing approaches rely on deep fusion, which obscures how individual modalities contribute to predictions and limits the interpretability of multimodal reasoning. We propose an explicit multimodal routing framework for clinical prediction that enables interpretable, robust, and auditable reasoning across three EHR modalities: structured longitudinal variables (L), clinical notes (N), and chest X-rays (I). Our model constructs discrete unimodal, directional bimodal, and trimodal routes to capture both individual modality signals and asymmetric cross-modal interactions. To audit multimodal reasoning and assess robustness, we introduce inference-time route masking, which simulates missing modalities and reweights the remaining routes without retraining. We analyze changes in performance and routing weights under these scenarios to understand model decision-making. We evaluate our framework on multi-label phenotype prediction (K = 25) and binary ICU mortality prediction using trimodal patient stays from MIMIC-IV, revealing systematic differences in modality reliance across clinical condition groups. Overall, our framework offers a transparent, auditable, and practical approach to multimodal clinical prediction, providing interpretability, robustness, and insights into how different data sources drive model decisions.

cs.LG↗

arXiv2026

Tensor Hypercontraction Error Correction Using Regression

Wavefunction-based quantum methods are some of the most accurate tools for predicting and analyzing the electronic structure of molecules, in particular for accounting for dynamical electron correlation. However, most methods of including dynamical correlation beyond the simple second-order M{\o}ller-Plesset perturbation theory (MP2) level are too computationally expensive to apply to large molecules. Approximations which reduce scaling with system size are a potential remedy, such as the tensor hyper-contraction (THC) technique of Hohenstein et al., but also result in additional sources of error. In this work, we correct errors in THC-approximated methods using machine learning. Specifically, we apply THC to third-order M{\o}ller-Plesset theory (MP3) as a simplified model for coupled cluster with single and double excitations (CCSD), and train several regression models on observed THC errors from the Main Group Chemistry Database (MGCDB84). We compare performance of multiple linear regression models and non-linear Kernel Ridge regression models. We also investigate correlation procedures using absolute and relative corrections and evaluate the corrections for both molecule and reaction energies. We discuss the potential for using regression techniques to correct THC-MP3 errors by comparing it to the "canonical" MP3 reference values and find the optimum technique based on accuracy. We find that non-linear regression models reduced root mean squared errors between THC- and canonical MP3 by a factor of 6-9$\times$ for total molecular energies and 2-3$\times$ for reaction energies.

physics.chem-ph↗

arXiv2026

2Mamba2Furious: Linear in Complexity, Competitive in Accuracy

Linear attention transformers have become a strong alternative to softmax attention due to their efficiency. However, linear attention tends to be less expressive and results in reduced accuracy compared to softmax attention. To bridge the accuracy gap between softmax attention and linear attention, we manipulate Mamba-2, a very strong linear attention variant. We first simplify Mamba-2 down to its most fundamental and important components, evaluating which specific choices make it most accurate. From this simplified Mamba variant (Mamba-2S), we improve the A-mask and increase the order of the hidden state, resulting in a method, which we call 2Mamba, that is nearly as accurate as softmax attention, yet much more memory efficient for long context lengths. We also investigate elements to Mamba-2 that help surpass softmax attention accuracy. Code is provided for all our experiments.

cs.LG↗

arXiv2025

On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective

Since its introduction, softmax attention has become the backbone of modern transformer architectures due to its expressiveness and scalability across a wide range of tasks. However, the main drawback of softmax attention is the quadratic memory requirement and computational complexity with respect to the sequence length. By replacing the softmax nonlinearity, linear attention and similar methods have been introduced to avoid the quadratic bottleneck of softmax attention. Despite these linear forms of attention being derived from the original softmax formulation, they typically lag in terms of downstream accuracy. While strong intuition of the softmax nonlinearity on the query and key inner product suggests that it has desirable properties compared to other nonlinearities, the question of why this discrepancy exists still remains unanswered. This work demonstrates that linear attention is an approximation of softmax attention by deriving the recurrent form of softmax attention. Using this form, each part of softmax attention can be described in the language of recurrent neural networks (RNNs). Describing softmax attention as an RNN allows for the ablation of the components of softmax attention to understand the importance of each part and how they interact. In this way, our work helps explain why softmax attention is more expressive than its counterparts.

cs.LG↗

arXiv2025

Equitable Electronic Health Record Prediction with FAME: Fairness-Aware Multimodal Embedding

Electronic Health Record (EHR) data encompass diverse modalities -- text, images, and medical codes -- that are vital for clinical decision-making. To process these complex data, multimodal AI (MAI) has emerged as a powerful approach for fusing such information. However, most existing MAI models optimize for better prediction performance, potentially reinforcing biases across patient subgroups. Although bias-reduction techniques for multimodal models have been proposed, the individual strengths of each modality and their interplay in both reducing bias and optimizing performance remain underexplored. In this work, we introduce FAME (Fairness-Aware Multimodal Embeddings), a framework that explicitly weights each modality according to its fairness contribution. FAME optimizes both performance and fairness by incorporating a combined loss function. We leverage the Error Distribution Disparity Index (EDDI) to measure fairness across subgroups and propose a sign-agnostic aggregation method to balance fairness across subgroups, ensuring equitable model outcomes. We evaluate FAME with BEHRT and BioClinicalBERT, combining structured and unstructured EHR data, and demonstrate its effectiveness in terms of performance and fairness compared with other baselines across multiple EHR prediction tasks.

cs.LG↗

arXiv2024

Cottention: Linear Transformers With Cosine Attention

Attention mechanisms, particularly softmax attention, have been instrumental in the success of transformer-based models such as GPT. However, the quadratic memory complexity of softmax attention with respect to sequence length poses significant challenges for processing longer sequences. We introduce Cottention, a novel attention mechanism that replaces the softmax operation with cosine similarity. By leveraging the properties of cosine similarity and rearranging the attention equation, Cottention achieves native linear memory complexity with respect to sequence length, making it inherently more memory-efficient than softmax attention. We demonstrate that Cottention can be reformulated as a recurrent neural network (RNN) with a finite hidden state, allowing for constant memory usage during inference. We evaluate Cottention on both the bidirectional BERT and causal GPT tasks, demonstrating comparable performance to softmax attention while significantly reducing memory requirements. To ensure efficient computation, we develop a custom CUDA kernel for Cottention. Our results show that Cottention is a promising alternative to softmax attention, enabling the processing of longer sequences without sacrificing performance, due to its native linear memory complexity and ability to maintain a constant memory footprint during inference.

cs.LG↗

arXiv2024

Scaling Continuous Kernels with Sparse Fourier Domain Learning

We address three key challenges in learning continuous kernel representations: computational efficiency, parameter efficiency, and spectral bias. Continuous kernels have shown significant potential, but their practical adoption is often limited by high computational and memory demands. Additionally, these methods are prone to spectral bias, which impedes their ability to capture high-frequency details. To overcome these limitations, we propose a novel approach that leverages sparse learning in the Fourier domain. Our method enables the efficient scaling of continuous kernels, drastically reduces computational and memory requirements, and mitigates spectral bias by exploiting the Gibbs phenomenon.

cs.LG↗

arXiv2024

Digit Recognition using Multimodal Spiking Neural Networks

Spiking neural networks (SNNs) are the third generation of neural networks that are biologically inspired to process data in a fashion that emulates the exchange of signals in the brain. Within the Computer Vision community SNNs have garnered significant attention due in large part to the availability of event-based sensors that produce a spatially resolved spike train in response to changes in scene radiance. SNNs are used to process event-based data due to their neuromorphic nature. The proposed work examines the neuromorphic advantage of fusing multiple sensory inputs in classification tasks. Specifically we study the performance of a SNN in digit classification by passing in a visual modality branch (Neuromorphic-MNIST [N-MNIST]) and an auditory modality branch (Spiking Heidelberg Digits [SHD]) from datasets that were created using event-based sensors to generate a series of time-dependent events. It is observed that multi-modal SNNs outperform unimodal visual and unimodal auditory SNNs. Furthermore, it is observed that the process of sensory fusion is insensitive to the depth at which the visual and auditory branches are combined. This work achieves a 98.43% accuracy on the combined N-MNIST and SHD dataset using a multimodal SNN that concatenates the visual and auditory branches at a late depth.

eess.AS↗

arXiv2024

Designing a Photonic Physically Unclonable Function Having Resilience to Machine Learning Attacks

Physically unclonable functions (PUFs) are designed to act as device 'fingerprints.' Given an input challenge, the PUF circuit should produce an unpredictable response for use in situations such as root-of-trust applications and other hardware-level cybersecurity applications. PUFs are typically subcircuits present within integrated circuits (ICs), and while conventional IC PUFs are well-understood, several implementations have proven vulnerable to malicious exploits, including those perpetrated by machine learning (ML)-based attacks. Such attacks can be difficult to prevent because they are often designed to work even when relatively few challenge-response pairs are known in advance. Hence the need for both more resilient PUF designs and analysis of ML-attack susceptibility. Previous work has developed a PUF for photonic integrated circuits (PICs). A PIC PUF not only produces unpredictable responses given manufacturing-introduced tolerances, but is also less prone to electromagnetic radiation eavesdropping attacks than a purely electronic IC PUF. In this work, we analyze the resilience of the proposed photonic PUF when subjected to ML-based attacks. Specifically, we describe a computational PUF model for producing the large datasets required for training ML attacks; we analyze the quality of the model; and we discuss the modeled PUF's susceptibility to ML-based attacks. We find that the modeled PUF generates distributions that resemble uniform white noise, explaining the exhibited resilience to neural-network-based attacks designed to exploit latent relationships between challenges and responses. Preliminary analysis suggests that the PUF exhibits similar resilience to generative adversarial networks, and continued development will show whether more-sophisticated ML approaches better compromise the PUF and -- if so -- how design modifications might improve resilience.

cs.CR↗

arXiv2024

A Photonic Physically Unclonable Function's Resilience to Multiple-Valued Machine Learning Attacks

Physically unclonable functions (PUFs) identify integrated circuits using nonlinearly-related challenge-response pairs (CRPs). Ideally, the relationship between challenges and corresponding responses is unpredictable, even if a subset of CRPs is known. Previous work developed a photonic PUF offering improved security compared to non-optical counterparts. Here, we investigate this PUF's susceptibility to Multiple-Valued-Logic-based machine learning attacks. We find that approximately 1,000 CRPs are necessary to train models that predict response bits better than random chance. Given the significant challenge of acquiring a vast number of CRPs from a photonic PUF, our results demonstrate photonic PUF resilience against such attacks.

cs.CR↗

arXiv2023

Demonstration of a Hardware-Independent Toolkit for Automated Quantum Subcircuit Synthesis

The quantum computer has become contemporary reality, with the first two-qubit machine of mere decades ago transforming into cloud-accessible devices with tens, hundreds, or -- in a few cases -- even thousands of qubits. While such hardware is noisy and still relatively small, the increasing number of operable qubits raises another challenge: how to develop the now-sizeable quantum circuits executable on these machines. Preparing circuits manually for specifications of any meaningful size is at best tedious and at worst impossible, creating a need for automation. This article describes an automated quantum-software toolkit for synthesis, compilation, and optimization, which transforms classically-specified, irreversible functions into both technology-independent and technology-dependent quantum circuits. We also describe and analyze the toolkit's application to three situations -- quantum read-only memories, quantum random number generators, and quantum oracles -- and illustrate the toolkit's start-to-finish features, from the input of classical functions to the output of technology-dependent quantum circuits. Furthermore, we illustrate how the toolkit enables research beyond circuit synthesis, including comparison of synthesis and optimization methods and deeper understanding of even well-studied quantum algorithms. As quantum hardware continues to develop, such quantum circuit toolkits will play a critical role in realizing its potential.

quant-ph↗

arXiv2023

CNN-Assisted Steganography -- Integrating Machine Learning with Established Steganographic Techniques

We propose a method to improve steganography by increasing the resilience of stego-media to discovery through steganalysis. Our approach enhances a class of steganographic approaches through the inclusion of a steganographic assistant convolutional neural network (SA-CNN). Previous research showed success in discovering the presence of hidden information within stego-images using trained neural networks as steganalyzers that are applied to stego-images. Our results show that such steganalyzers are less effective when SA-CNN is employed during the generation of a stego-image. We also explore the advantages and disadvantages of representing all the possible outputs of our SA-CNN within a smaller, discrete space, rather than a continuous space. Our SA-CNN enables certain classes of parametric steganographic algorithms to be customized based on characteristics of the cover media in which information is to be embedded. Thus, SA-CNN is adaptive in the sense that it enables the core steganographic algorithm to be especially configured for each particular instance of cover media. Experimental results are provided that employ a recent steganographic technique, S-UNIWARD, both with and without the use of SA-CNN. We then apply both sets of stego-images, those produced with and without SA-CNN, to an exmaple steganalyzer, Yedroudj-Net, and we compare the results. We believe that this approach for the integration of neural networks with hand-crafted algorithms increases the reliability and adaptability of steganographic algorithms.

cs.CR↗

arXiv2023

A Programmable True Random Number Generator Using Commercial Quantum Computers

Random number generators (RNG) are essential elements in many cryptographic systems. True random number generators (TRNG) rely upon sources of randomness from natural processes such as those arising from quantum mechanics phenomena. We demonstrate that a quantum computer can serve as a high-quality, weakly random source for a generalized user-defined probability mass function (PMF). Specifically, QC measurement implements the process of variate sampling according to a user-specified PMF resulting in a word comprised of electronic bits that can then be processed by an extractor function to address inaccuracies due to non-ideal quantum gate operations and other system biases. We introduce an automated and flexible method for implementing a TRNG as a programmed quantum circuit that executes on commercially-available, gate-model quantum computers. The user specifies the desired word size as the number of qubits and a definition of the desired PMF. Based upon the user specification of the PMF, our compilation tool automatically synthesizes the desired TRNG as a structural OpenQASM file containing native gate operations that are optimized to reduce the circuit's quantum depth. The resulting TRNG provides multiple bits of randomness for each execution/measurement cycle; thus, the number of random bits produced in each execution is limited only by the size of the QC. We provide experimental results to illustrate the viability of this approach.

quant-ph↗

arXiv2022

LAST: Latent Space Assisted Adaptive Sampling for Protein Trajectories

Molecular dynamics (MD) simulation is widely used to study protein conformations and dynamics. However, conventional simulation suffers from being trapped in some local energy minima that are hard to escape. Thus, most computational time is spent sampling in the already visited regions. This leads to an inefficient sampling process and further hinders the exploration of protein movements in affordable simulation time. The advancement of deep learning provides new opportunities for protein sampling. Variational autoencoders are a class of deep learning models to learn a low-dimensional representation (referred to as the latent space) that can capture the key features of the input data. Based on this characteristic, we proposed a new adaptive sampling method, latent space assisted adaptive sampling for protein trajectories (LAST), to accelerate the exploration of protein conformational space. This method comprises cycles of (i) variational autoencoders training, (ii) seed structure selection on the latent space and (iii) conformational sampling through additional MD simulations. The proposed approach is validated through the sampling of four structures of two protein systems: two metastable states of E. Coli adenosine kinase (ADK) and two native states of Vivid (VVD). In all four conformations, seed structures were shown to lie on the boundary of conformation distributions. Moreover, large conformational changes were observed in a shorter simulation time when compared with conventional MD (cMD) simulations in both systems. In metastable ADK simulations, LAST explored two transition paths toward two stable states while cMD became trapped in an energy basin. In VVD light state simulations, LAST was three times faster than cMD simulation with a similar conformational space.

q-bio.QM↗

arXiv2021

Smartphone Camera Oximetry in an Induced Hypoxemia Study

Hypoxemia, a medical condition that occurs when the blood is not carrying enough oxygen to adequately supply the tissues, is a leading indicator for dangerous complications of respiratory diseases like asthma, COPD, and COVID-19. While purpose-built pulse oximeters can provide accurate blood-oxygen saturation (SpO$_2$) readings that allow for diagnosis of hypoxemia, enabling this capability in unmodified smartphone cameras via a software update could give more people access to important information about their health, as well as improve physicians' ability to remotely diagnose and treat respiratory conditions. In this work, we take a step towards this goal by performing the first clinical development validation on a smartphone-based SpO$_2$ sensing system using a varied fraction of inspired oxygen (FiO$_2$) protocol, creating a clinically relevant validation dataset for solely smartphone-based methods on a wide range of SpO$_2$ values (70%-100%) for the first time. This contrasts with previous studies, which evaluated performance on a far smaller range (85%-100%). We build a deep learning model using this data to demonstrate accurate reporting of SpO$_2$ level with an overall MAE=5.00% SpO$_2$ and identifying positive cases of low SpO$_2$<90% with 81% sensitivity and 79% specificity. We ground our analysis with a summary of recent literature in smartphone-based SpO2 monitoring, and we provide the data from the FiO$_2$ study in open-source format, so that others may build on this work.

cs.LG↗

arXiv2021

On the Interpretability of Deep Learning Based Models for Knowledge Tracing

Knowledge tracing allows Intelligent Tutoring Systems to infer which topics or skills a student has mastered, thus adjusting curriculum accordingly. Deep Learning based models like Deep Knowledge Tracing (DKT) and Dynamic Key-Value Memory Network (DKVMN) have achieved significant improvements compared with models like Bayesian Knowledge Tracing (BKT) and Performance Factors Analysis (PFA). However, these deep learning based models are not as interpretable as other models because the decision-making process learned by deep neural networks is not wholly understood by the research community. In previous work, we critically examined the DKT model, visualizing and analyzing the behaviors of DKT in high dimensional space. In this work, we extend our original analyses with a much larger dataset and add discussions about the memory states of the DKVMN model. We discover that Deep Knowledge Tracing has some critical pitfalls: 1) instead of tracking each skill through time, DKT is more likely to learn an `ability' model; 2) the recurrent nature of DKT reinforces irrelevant information that it uses during the tracking task; 3) an untrained recurrent network can achieve similar results to a trained DKT model, supporting a conclusion that recurrence relations are not properly learned and, instead, improvements are simply a benefit of projection into a high dimensional, sparse vector space. Based on these observations, we propose improvements and future directions for conducting knowledge tracing research using deep neural network models.

cs.LG↗

arXiv2021

Writers Gonna Wait: The Effectiveness of Notifications to Initiate Aversive Action in Writing Procrastination

This paper evaluates the use of notifications to reduce aversive-task-procrastination by helping initiate action. Specifically, we focus on aversion to graded writing tasks. We evaluate software designs commonly used by behavior change applications, such as goal setting and action support systems. We conduct a two-phase control trial experiment with 21 college students tasked to write two 3000-word writing assignments (14 students fully completed the experiment). Participants use a customized text editor designed to continuously collect writing behavior. The results from the study reveal that notifications have minimal effect in encouraging users to get started. They can also increase negative effects on participants. Other techniques, such as eliminating distraction and showing simple writing statistics, yield higher satisfaction among participants as they complete the writing task. Furthermore, the incorporation of text mining decreases aversion to the task and helps participants overcome writer's block. Finally, we discuss lessons learned from our evaluation that help quantify the difficulty of behavior change for writing procrastination, with emphasis on goals for the HCI community.

cs.HC↗

arXiv2021

AirWare: Utilizing Embedded Audio and Infrared Signals for In-Air Hand-Gesture Recognition

We introduce AirWare, an in-air hand-gesture recognition system that uses the already embedded speaker and microphone in most electronic devices, together with embedded infrared proximity sensors. Gestures identified by AirWare are performed in the air above a touchscreen or a mobile phone. AirWare utilizes convolutional neural networks to classify a large vocabulary of hand gestures using multi-modal audio Doppler signatures and infrared (IR) sensor information. As opposed to other systems which use high frequency Doppler radars or depth cameras to uniquely identify in-air gestures, AirWare does not require any external sensors. In our analysis, we use openly available APIs to interface with the Samsung Galaxy S5 audio and proximity sensors for data collection. We find that AirWare is not reliable enough for a deployable interaction system when trying to classify a gesture set of 21 gestures, with an average true positive rate of only 50.5% per gesture. To improve performance, we train AirWare to identify subsets of the 21 gestures vocabulary based on possible usage scenarios. We find that AirWare can identify three gesture sets with average true positive rate greater than 80% using 4--7 gestures per set, which comprises a vocabulary of 16 unique in-air gestures.

cs.HC↗