Searcharxiv⌕ Search

arXiv subjects

Daniel Chen

Publications and source records attributed to Daniel Chen.

At least 19 recordsLinked to original sources
arXiv2026

Titans-as-a-Layer: Test-Time Memory for Conversational Speech Emotion Recognition

Speech emotion recognition (SER) is commonly formulated as utterance-level classification, although conversational emotion depends on a speaker's usual vocal range and the emotional context established by previous utterances. Speech-language models provide strong pretrained acoustic and semantic representations, and can adapts them to SER labels via finetune, but this mechanism still missing per-dialogue state. We study whether test-time neural memory can supply this missing context while leaving the large audio language models (LALMs) backbone intact. Building on Titans, we introduce a plug-and-play Memory-as-a-Layer (MAL) adapter that writes dialogue history into a small neural memory and reads it back as an audio-token-aligned residual update, avoiding changes to the host model's token positions. Across different audio LLMs and emotion recognition datasets evaluations, our design improves SER performs across different evaluation metrics, supporting test-time memory as a residual contextual mechanism for conversational SER.

cs.LG↗
arXiv2026

Array Layout Optimization in a 24-Element 38-GHz Active Incoherent Millimeter-Wave Imaging System

Active incoherent millimeter-wave (AIM) imaging is a recently developed technique that has been shown to generate fast millimeter-wave imaging using sparse apertures and Fourier domain sampling. In these systems, spatial frequency sampling is determined by cross-correlation between antenna pairs, making array geometry an important aspect that dictates the field of view (FOV) and image quality. This work investigates the impact of array redundancy and spatial sampling diversity on AIM image reconstruction performance. We present a comparative study of three receive array configurations, including one simple circular design and two arrays obtained through optimization strategies designed to maximize unique spatial samples while preserving system resolution and FOV. Performance is evaluated using the image-domain metrics of structural similarity index (SSIM) and peak sidelobe level (PSL), enabling a quantitative assessment of reconstruction fidelity and artifact suppression. We perform experimental validation using a 38-GHz AIM imaging system, implementing a 24-element receive array within a 48-position reconfigurable aperture. Results demonstrate that optimized array configurations improve spatial sampling efficiency and yield measurable gains in reconstruction quality compared to a conventional circular array, highlighting the importance of array design for AIM imaging systems.

eess.SP↗
arXiv2026

Dynamic Decision-Making under Model Misspecification: A Stochastic Stability Approach

Dynamic decision-making under model uncertainty is central to many economic environments, yet existing bandit and reinforcement learning algorithms rely on the assumption of correct model specification. This paper studies the behavior and performance of one of the most commonly used Bayesian reinforcement learning algorithms, Thompson Sampling (TS), when the model class is misspecified. We first provide a complete dynamic classification of posterior evolution in a misspecified two-armed Gaussian bandit, identifying distinct regimes: correct model concentration, incorrect model concentration, and persistent belief mixing, characterized by the direction of statistical evidence and the model-action mapping. These regimes yield sharp predictions for limiting beliefs, action frequencies, and asymptotic regret. We then extend the analysis to a general finite model class and develop a unified stochastic stability framework that represents posterior evolution as a Markov process on the belief simplex. This approach characterizes two sufficient conditions to classify the ergodic and transient behaviors and provides inductive dimensional reductions of the posterior dynamics. Our results offer the first qualitative and geometric classification of TS under misspecification, bridging Bayesian learning with evolutionary dynamics, and also build the foundations of robust decision-making in structured bandits.

econ.TH↗
arXiv2026

Parameter-Efficient Fine-Tuning of DINOv2 for Large-Scale Font Classification

We introduce GoogleFontsBench, the first public benchmark for classifying open-source web fonts, addressing a gap left by existing benchmarks that cover only commercial typefaces. GoogleFontsBench comprises 394 font variants across 32 Google Fonts families, a reproducible synthetic data generation pipeline (~575 images per variant, ~226K total), and a typographically-grounded evaluation metric (SWER) that weights errors by visual severity. We establish baselines using six fine-tuning strategies on a DINOv2 Vision Transformer backbone. Parameter-efficient adaptation with LoRA achieves 99.0% top-1 accuracy while training only 1% of the model's 87.2M parameters, with errors 140x less severe than random guessing. We release the benchmark, all trained models, and the full training pipeline as open-source resources.

cs.CV↗
arXiv2024

Imageless Contraband Detection Using a Millimeter-Wave Dynamic Antenna Array via Spatial Fourier Domain Sampling

We demonstrate an imageless method of concealed contraband detection using a real-time 75 GHz rotationally dynamic antenna array. The array measures information in the two-dimensional Fourier domain and captures a set of samples that is sufficient for detecting concealed objects yet insufficient for generating full image, thereby preserving the privacy of screened subjects. The small set of Fourier samples contains sharp spatial frequency features in the Fourier domain which correspond to sharp edges of man-made objects such as handguns. We evaluate a set of classification methods: threshold-based, K-nearest neighbor, and support vector machine using radial basis function; all operating on arithmetic features directly extracted from the sampled Fourier-domain responses measured by a dynamically rotating millimeter-wave active interferometer. Noise transmitters are used to produce thermal-like radiation from scenes, enabling direct Fourier-domain sampling, while the rotational dynamics circularly sample the two-dimensional Fourier domain, capturing the sharp-edge induced responses. We experimentally demonstrate the detection of concealed metallic gun-shape object beneath clothing on a real person in a laboratory environment and achieved an accuracy and F1-score both at 0.986. The presented technique not only prevents image formation due to efficient Fourier-domain space sub-sampling but also requires only 211 ms from measurement to decision.

eess.SP↗
arXiv2023

Expected Number of Dice Rolls Until an Increasing Run of Three

A closed form is found for the expected number of rolls of a fair n-sided die until three consecutive increasing values are seen. The answer is rational, and the greatest common divisor of the numerator and denominator is given in terms of n. As n goes to infinity, the probability generating function is found for the limiting case, which is also the exponential generating function for permutations ending in a double rise and without other double rises. Thus exact values are found for the limiting expectation and variance, which are approximately 7.92437 and 27.98133 respectively.

math.CO↗
arXiv2023

Semi-automated extraction of research topics and trends from NCI funding in radiological sciences from 2000-2020

Investigators, funders, and the public desire knowledge on topics and trends in publicly funded research but current efforts in manual categorization are limited in scale and understanding. We developed a semi-automated approach to extract and name research topics, and applied this to \$1.9B of NCI funding over 21 years in the radiological sciences to determine micro- and macro-scale research topics and funding trends. Our method relies on sequential clustering of existing biomedical-based word embeddings, naming using subject matter experts, and visualization to discover trends at a macroscopic scale above individual topics. We present results using 15 and 60 cluster topics, where we found that 2D projection of grant embeddings reveals two dominant axes: physics-biology and therapeutic-diagnostic. For our dataset, we found that funding for therapeutics- and physics-based research have outpaced diagnostics- and biology-based research, respectively. We hope these results may (1) give insight to funders on the appropriateness of their funding allocation, (2) assist investigators in contextualizing their work and explore neighboring research domains, and (3) allow the public to review where their tax dollars are being allocated.

cs.CL↗
arXiv2023

Explicitly Solvable Continuous-time Inference for Partially Observed Markov Processes

Many natural and engineered systems can be modeled as discrete state Markov processes. Often, only a subset of states are directly observable. Inferring the conditional probability that a system occupies a particular hidden state, given the partial observation, is a problem with broad application. In this paper, we introduce a continuous-time formulation of the sum-product algorithm, which is a well-known discrete-time method for finding the hidden states' conditional probabilities, given a set of finite, discrete-time observations. From our new formulation, we can explicitly solve for the conditional probability of occupying any state, given the transition rates and observations within a finite time window. We apply our algorithm to a realistic model of the cystic fibrosis transmembrane conductance regulator (CFTR) protein for exact inference of the conditional occupancy probability, given a finite time series of partial observations.

eess.SP↗
arXiv2022

Approximate Quantum Circuit Cutting

Current and imminent quantum hardware lacks reliability and applicability due to noise and limited qubit counts. Quantum circuit cutting -- a technique dividing large quantum circuits into smaller subcircuits with sizes appropriate for the limited quantum resource at hand -- is used to mitigate these problems. However, classical postprocessing involved in circuit cutting generally grows exponentially with the number of cuts and quantum counts. This article introduces the notion of approximate circuit reconstruction. Using a sampling-based method like Markov Chain Monte Carlo (MCMC), we probabilistically select bit strings of high probability upon reconstruction. This avoids excessive calculations when reconstructing the full probability distribution. Our results show that such a sampling-based postprocessing method holds great potential for fast and reliable circuit reconstruction in the NISQ era and beyond.

quant-ph↗
arXiv2022

Associated Permutations of Complete Non-Ambiguous Trees

We explore new connections between complete non-ambiguous trees (CNATs) and permutations. We give a bijection between tree-like tableaux and a specific subset of CNATs. This map is used to establish and solve a recurrence relation for the number of tree-like tableaux of a fixed size without occupied corners, proving a conjecture by Laborde-Zubieta. We end by establishing a row/column swapping operation on CNATs and identify new areas for future research.

math.CO↗
arXiv2021

QuClassi: A Hybrid Deep Neural Network Architecture based on Quantum State Fidelity

In the past decade, remarkable progress has been achieved in deep learning related systems and applications. In the post Moore's Law era, however, the limit of semiconductor fabrication technology along with the increasing data size have slowed down the development of learning algorithms. In parallel, the fast development of quantum computing has pushed it to the new ear. Google illustrates quantum supremacy by completing a specific task (random sampling problem), in 200 seconds, which is impracticable for the largest classical computers. Due to the limitless potential, quantum based learning is an area of interest, in hopes that certain systems might offer a quantum speedup. In this work, we propose a novel architecture QuClassi, a quantum neural network for both binary and multi-class classification. Powered by a quantum differentiation function along with a hybrid quantum-classic design, QuClassi encodes the data with a reduced number of qubits and generates the quantum circuit, pushing it to the quantum platform for the best states, iteratively. We conduct intensive experiments on both the simulator and IBM-Q quantum platform. The evaluation results demonstrate that QuClassi is able to outperform the state-of-the-art quantum-based solutions, Tensorflow-Quantum and QuantumFlow by up to 53.75% and 203.00% for binary and multi-class classifications. When comparing to traditional deep neural networks, QuClassi achieves a comparable performance with 97.37% fewer parameters.

quant-ph↗
arXiv2020

Quantum-Inspired Classical Algorithm for Slow Feature Analysis

Recently, there has been a surge of interest for quantum computation for its ability to exponentially speed up algorithms, including machine learning algorithms. However, Tang suggested that the exponential speed up can also be done on a classical computer. In this paper, we proposed an algorithm for slow feature analysis, a machine learning algorithm that extracts the slow-varying features, with a run time O(polylog(n)poly(d)). To achieve this, we assumed necessary preprocessing of the input data as well as the existence of a data structure supporting a particular sampling scheme. The analysis of algorithm borrowed results from matrix perturbation theory, which was crucial for the algorithm's correctness. This work demonstrates the possible application and extent for which quantum-inspired computation can be used.

cs.DM↗
arXiv2020

QuGAN: A Quantum State Fidelity based Generative Adversarial Network

Tremendous progress has been witnessed in artificial intelligence where neural network backed deep learning systems have been used, with applications in almost every domain. As a representative deep learning framework, Generative Adversarial Network (GAN) has been widely used for generating artificial images, text-to-image or image augmentation across areas of science, arts and video games. However, GANs are computationally expensive, sometimes computationally prohibitive. Furthermore, training GANs may suffer from convergence failure and modal collapse. Aiming at the acceleration of use cases for practical quantum computers, we propose QuGAN, a quantum GAN architecture that provides stable convergence, quantum-state based gradients and significantly reduced parameter sets. The QuGAN architecture runs both the discriminator and the generator purely on quantum state fidelity and utilizes the swap test on qubits to calculate the values of quantum-based loss functions. Built on quantum layers, QuGAN achieves similar performance with a 94.98% reduction on the parameter set when compared to classical GANs. With the same number of parameters, additionally, QuGAN outperforms state-of-the-art quantum based GANs in the literature providing a 48.33% improvement in system performance compared to others attaining less than 0.5% in terms of similarity between generated distributions and original data sets. QuGAN code is released at https://github.com/yingmao/Quantum-Generative-Adversarial-Network

quant-ph↗
arXiv2020

Quantum-Inspired Classical Algorithm for Principal Component Regression

This paper presents a sublinear classical algorithm for principal component regression. The algorithm uses quantum-inspired linear algebra, an idea developed by Tang. Using this technique, her algorithm for recommendation systems achieved runtime only polynomially slower than its quantum counterpart. Her work was quickly adapted to solve many other problems in sublinear time complexity. In this work, we developed an algorithm for principal component regression that runs in time polylogarithmic to the number of data points, an exponential speed up over the state-of-the-art algorithm, under the mild assumption that the input is given in some data structure that supports a norm-based sampling procedure. This exponential speed up allows for potential applications in much larger data sets.

cs.LG↗
arXiv2019

Understanding Fault Scenarios and Impacts through Fault Injection Experiments in Cielo

We present a set of fault injection experiments performed on the ACES (LANL/SNL) Cray XE supercomputer Cielo. We use this experimental campaign to improve the understanding of failure causes and propagation that we observed in the field failure data analysis of NCSA's Blue Waters. We use the data collected from the logs and from network performance counter data 1) to characterize the fault-error-failure sequence and recovery mechanisms in the Gemini network and in the Cray compute nodes, 2) to understand the impact of failures on the system and the user applications at different scale, and 3) to identify and recreate fault scenarios that induce unrecoverable failures, in order to create new tests for system and application design. The faults were injected through special input commands to bring down network links, directional connections, nodes, and blades. We present extensions that will be needed to apply our methodologies of injection and analysis to the Cray XC (Aries) systems.

cs.DC↗
arXiv2018

Information Acquisition and Time-Risk Preference

An agent acquires information dynamically until her belief about a binary state reaches an upper or lower threshold. She can choose any signal process subject to a constraint on the rate of entropy reduction. Strategies are ordered by "time risk"-the dispersion of the distribution of threshold-hitting times. We construct a strategy maximizing time risk (Greedy Exploitation) and one minimizing it (Pure Accumulation). Under either strategy, beliefs follow a compensated Poisson process. In the former, beliefs jump to the threshold that is closer in Bregman divergence. In the latter, beliefs jump to the unique point with the same entropy as the current belief.

econ.TH↗
arXiv2015

Systems-theoretic Safety Assessment of Robotic Telesurgical Systems

Robotic telesurgical systems are one of the most complex medical cyber-physical systems on the market, and have been used in over 1.75 million procedures during the last decade. Despite significant improvements in design of robotic surgical systems through the years, there have been ongoing occurrences of safety incidents during procedures that negatively impact patients. This paper presents an approach for systems-theoretic safety assessment of robotic telesurgical systems using software-implemented fault-injection. We used a systemstheoretic hazard analysis technique (STPA) to identify the potential safety hazard scenarios and their contributing causes in RAVEN II robot, an open-source robotic surgical platform. We integrated the robot control software with a softwareimplemented fault-injection engine which measures the resilience of the system to the identified safety hazard scenarios by automatically inserting faults into different parts of the robot control software. Representative hazard scenarios from real robotic surgery incidents reported to the U.S. Food and Drug Administration (FDA) MAUDE database were used to demonstrate the feasibility of the proposed approach for safety-based design of robotic telesurgical systems.

cs.RO↗