Designing effective quantum circuits remains a central challenge in quantum computing, as circuit structure strongly influences expressivity, trainability, and hardware feasibility. Current approaches, whether using manually designed circuit templates, fixed heuristics, or automated rules, face limitations in scalability, flexibility, and adaptability, often producing circuits that are poorly matched to the specific problem or quantum hardware. In this work, we propose the Evolutionary eXploration of Augmenting Quantum Circuits (EXAQC), an evolutionary approach to the automated design and training of parameterized quantum circuits (PQCs) which leverages and extends on strategies from neuroevolution and genetic programming. The proposed method jointly searches over gate types, qubit connectivity, parameterization, and circuit depth while respecting hardware and noise constraints. The method supports both Qiskit and Pennylane libraries, allowing the user to configure every aspect. This work highlights evolutionary search as a critical tool for advancing quantum machine learning and variational quantum algorithms, providing a principled pathway toward scalable, problem-aware, and hardware-efficient quantum circuit design. Preliminary results demonstrate that circuits evolved on classification tasks are able to achieve over 90% accuracy on most of the benchmark datasets with a limited computational budget, and are able to emulate target circuit quantum states with high fidelity scores.

Our goal is to educate individuals on how to create technology that is fair, responsible, and respectful of all people and communities. Too often, software is developed without considering important ethical dimensions such as bias, privacy, or transparency, which can result in harmful or exclusionary outcomes, particularly in fields like healthcare, education, and finance. To provide accessible educational resources as well as spread awareness of the importance of ethical decision-making in computing, we created a collection of labs referred to as the Accessible Learning Labs (ALL). This demo focuses on three of those labs on the topic of ethics: one addresses algorithmic bias and how inequities can emerge from flawed data or design choices, another focuses on machine learning bias, and the third regarding bias in machine learning. All labs are accessible through only an internet connection and browser. They do not require additional software, making them easy to incorporate into classroom curricula or workshops. Each includes a reading on the topic, an activity that illustrates an ethical challenge and how to address it, reinforcement material with additional context, and lastly, a quiz to check comprehension. Complete project material is available at http://labs4all.org/

Accessibility remains underrepresented in undergraduate computing curricula, despite its critical role in modern software development. This poster presents an upper-level elective in Accessible Software Engineering that addresses this gap by (1) integrating accessibility principles through web-based, experiential labs and (2) leveraging AI agents that simulate users with diverse disabilities to support empathetic, role-based learning. The hands-on labs provide practical experience recognizing accessibility barriers and applying inclusive design strategies, while the AI agent interactions enable students to gather requirements directly from the perspectives of users with visual, cognitive, learning, and motor impairments. This approach helps students transform abstract accessibility standards into meaningful, actionable design decisions. Student feedback and project outcomes demonstrated substantial gains in accessibility awareness, technical competence, and human-centered design skills. The course model offers a scalable pathway for strengthening accessibility education within the computing curriculum.

Quantum error mitigation (QEM) is essential for extracting reliable results from near-term quantum devices, yet practical deployments must balance mitigation strength against runtime overhead under time-varying noise. We introduce GSC-QEMit, a telemetry-driven, context–forecast–bandit framework for adaptive mitigation that switches between lightweight suppression and heavier intervention as drift evolves. GSC-QEMit composes three coupled modules: (G) a Growing Hierarchical Self-Organizing Map (GHSOM) that clusters streaming telemetry into operating contexts; (S) an uncertainty-aware subsampled Gaussian-process forecaster that predicts short-horizon fidelity degradation; and (C) a cost-aware contextual multi-armed bandit (CMAB) that selects mitigation actions via Thompson sampling with explicit intervention cost. We evaluate GSC-QEMit on benchmark circuit families (GHZ, Quantum Fourier Transform, and Grover search) under nonstationary noise regimes simulated in Qiskit Aer, using an instrumented testbed where action labels correspond to graded mitigation intensity. Across Clifford, non-Clifford, and structured workloads, GSC-QEMit improves average logical fidelity by +9.0% relative to unmitigated execution while reducing unnecessary heavy interventions by reserving them for inferred noise spikes. The resulting policies exhibit a favorable fidelity–cost trade-off and transfer across the evaluated workloads without circuit-specific tuning.

Stock trading has always been a challenging task due to the highly volatile nature of the stock market. Making trading decisions to generate profit is particularly difficult under such conditions. To address this, we propose four novel loss functions to drive trading strategies for a portfolio of stocks. These loss functions account for the potential profits or losses associated with buying or shorting respective stocks, enabling potentially any artificial neural network to directly learn trading decisions. Despite the high volatility in stock market fluctuations over time, training time-series models such as transformers using these loss functions resulted in trading strategies that generated strong returns on a portfolio of 50 different S&P 500 company stocks compared to benchmark reinforcement learning techniques and a baseline buy and hold method. As an example, using 2021, 2022 and 2023 as three test periods, the Crossformer model adapted with our best loss function was most consistent, resulting in returns of 51.42%, 51.04% and 48.62% respectively. By comparison, leading reinforcement learning models such as PPO, DDPG, and deep RL portfolio management techniques achieved lower returns for the same periods. Our approach was also shown to generalize across portfolios, achieving favorable performance on two other distinct portfolios with 30 and 10 companies. These results suggest that profit-guided loss functions provide a promising approach for aligning model training with downstream trading objectives.

This paper extends Evolutionary eXploration of Augmenting Quantum Circuits (EXAQC), a unified framework for the automated design and optimization of parameterized quantum circuits (PQCs) to include reinforcement learning tasks. Designing effective quantum circuits is challenging as the performance of a circuit is highly dependent on architecture, including gate composition, qubit interactions, and depth, as well as the target quantum system. Traditional approaches relying on fixed templates or heuristic designs often fail to generalize across tasks. To address this, EXAQC formulates circuit construction as a distributed evolutionary optimization problem, jointly exploring circuit structure and parameters in parallel worker processes using mutation and crossover operators. Experiments on 4 standard classification benchmarks demonstrate that EXAQC achieves competitive or superior accuracy with more efficient circuits. Additionally, evaluations on 4 different reinforcement learning environments show that evolved circuits can learn effective policies and reach near-optimal rewards with relatively low parameter counts. Overall, EXAQC provides a scalable, task-adaptive approach for quantum circuit discovery, highlighting the potential of evolutionary methods in advancing quantum machine learning.

Accessibility is a crucial component in developing inclusive software. However, studies reveal that much of today's software is not designed with accessibility in mind. This issue is compounded by the fact that students often lack an understanding of both how to create accessible software and why it is important. To address this educational gap, we developed a set of labs known as Accessible Learning Labs (ALL). These experiential labs aim to teach participants the proper methods for creating accessible software while highlighting the significance of inclusivity. Additionally, these labs allow students to experience the effects of inaccessible software firsthand and apply corrective measures to improve accessibility. All project materials are freely accessible on the project website: https://all.rit.edu. This demo will involve a step-by-step walkthrough of two of our labs, Lab 2: Accessibility to Color Blindness, and Lab 9: Accessibility to Localization. Both of these labs employ an active learning model and comprise of five subsections: an about section, a reading section, an exercise section, a reinforcement section, and a quiz section. During the demo, we will showcase each of the five sections for both Lab 2 and Lab 9, which will allow users to learn about the background of the accessibility issue, experience the issue firsthand, and reinforce and test their knowledge of the accessibility topic. Attendees will learn how to use these labs to design customized learning experiences that align with the specific objectives of various courses and programs.

The Learning Using Statistical Invariants (LUSI) method is designed to integrate domain knowledge into machine learning models using structured elements referred to as “predicates.”This approach aims to improve model performance and reduce the amount of data required for training by leveraging the inherent properties of the domain. However, through a thorough theoretical analysis and numerical experiments, we demonstrate that LUSI often falls short of its intended goal. Our findings reveal significant flaws in the current formulation of LUSI; instead of effectively narrowing the set of admissible functions, the predicates act primarily as constraints on the output of the model, which can often lead to underwhelming performance and limited generalization. While LUSI may produce marginal improvements under specific conditions, its overall limitations and inability to consistently deliver intelligence-driven enhancements suggest a need for further refinement. Despite the identified limitations, the introduction of LUSI represents a timely and important step towards integrating domain-specific knowledge into machine learning, highlighting a promising direction for future research and development.

Ensuring accessibility is essential for developing software that is inclusive for all users. Unfortunately, research shows that a significant portion of modern software fails to meet accessibility standards. Many students not only lack the knowledge of how to create accessible software but also do not fully grasp why it matters. To bridge this educational gap, we created a series of labs called the Accessible Learning Labs (ALL). These labs are designed to teach the techniques for developing accessible software, while also emphasizing the importance of accessibility in software design. Through hands-on activities, students can experience the consequences of inaccessible software and learn to fix these issues to make the software more accessible. This collection of labs is beneficial to learners at various stages, from beginners to professionals looking to improve their skills in creating accessible software. All materials are available on the project website: https://all.rit.edu

Research demonstrates that we continue to be de-ficient in creating inclusive and equitable software, with a lack of empathy among software developers attributed to this issue, even if unintentional. Although increasing empathy has been shown to be part of the solution, unfortunately there is a lack of data that can be analyzed that shows how empathy-building and accessibility awareness interventions can be utilized in computing education, along with a shortage of free, public, and easily adoptable educational material regarding empathy and the creation of accessible software. Through large in-person studies that involve real-world par-ticipants, we are able to contribute to the knowledge regarding the potential benefits that can be used to improve computing education by implementing empathy-building strategies in the curriculum. Two forms of accessibility awareness exercises are utilized to display the effectiveness of empathy-based learning and teach the importance of accessibility in computing, including experiential and expression-based interventions. In these inter-ventions, we expect to find an increase in awareness and empathy in participants, as well as an increase in participant interest in the topic of software inclusivity and accessibility by placing the participant in a situation they may encounter in the real world. We additionally present a web-hosted, easily adoptable ex-periential and expression-based educational lab to support the inclusion of inclusive development and/or empathy-focused topics into a variety of curricula formats. Complete materials are available on the project website: https://all.rit.edu

This research full paper presents a study demonstrating the importance of empathy-building content in computing education to foster appreciation for accessible software. Past research identifies a lack of empathy among developers contributing to software inclusion issues. We propose that enhancing empathy can lead to more accessible and equitable software development. Despite empathy studies in other fields, integrating empathy into computing education lacks sufficient pedagogical insights and accessible resources. To address these gaps, we conducted an in-person study with 121 participants, using a randomized experimental design with two empathy-building intervention groups. We compared their responses to pre-/post-survey questions using statistical tests, examining experiential and expression-based interventions' impact on inclusiveness interest and awareness of non-inclusive software. Our research questions focused on whether these interventions increase the interest, awareness, and empathy of participants and if they are equally effective across demographics and intervention formats. Our findings demonstrate that empathy-building interventions effectively raise awareness and empathy among participants. Expression-based interventions significantly increase empathy and awareness across age and gender groups, with no significant differences in impact between experiential and expression-based methods. Furthermore, we provide an easily adoptable web-based educational lab to integrate empathy and inclusive development topics into diverse curricula formats, accessible via our project website: https://all.rit.edu

Artificial intelligence (AI) is becoming increasingly prevalent in our society, leading to a growing demand for a skilled workforce in AI. Unfortunately, this demand remains unmet, particularly among smaller institutions and those serving underrepresented groups, due to resource limitations. This initiative offers two hands-on educational activities in Artificial Intelligence and Machine Learning to facilitate the integration of AI/ML concepts into foundational computing and non-computing courses. While primarily aimed at undergraduate students, the materials created can also benefit high school (grades 9-12) and graduate students in various educational settings, including traditional classrooms and outreach or after-school programs. Labs are accessible through a web browser, making them easy to adopt at all institutions, especially those with limited resources. The self-contained and hosted nature of the labs ensures that they can be adopted by institutions facing resource constraints. The complete project material is publicly available on the project website: https://all.rit.edu

Accessibility is a key aspect in ensuring the development of inclusive software. Unfortunately, research demonstrates that a large portion of software today is not created in an accessible manner. Problematically, students may not understand how to create accessible software, additionally misunderstanding the importance of creating accessible software. To fill the gap in accessibility education, we have created a comprehensive collection of labs, collectively referred to as Accessible Learning Labs (ALL). They have the primary objectives of educating participants on how to properly create accessible software, simultaneously illustrating the need to create inclusive and accessible software. In addition, the lab activities enable students to experience the implications of inaccessible software and make repairs based on their experience, making the software in the labs accessible. This will benefit many members of the software engineering community, ranging from beginning-level students to experienced practitioners who want to ensure that they are properly creating accessible and inclusive software. Complete project material is publicly available on the project website: https://all.rit.edu

The traditional approach to data-driven learning has become increasingly demanding in terms of its training data and computational resources. This work further develops a new paradigm of learning using predicates to reduce the need of data in learning. Among many recent efforts towards the same direction, learning using statistical invariants (LUSI) has been proposed to be the new paradigm of learning. Building on top of LUSI and to break the ``brute force'' learning trend, we build towards a generalized theory of predicates and the invariants. The primary objective of this work is to propose an Extended Structure Risk Minimization (ESRM) paradigm with predicates, and provide a theoretical justification of the need for predicates in learning problems from both data complexity and model complexity perspectives. In this work, we show that predicates not only can aid in reducing the need for data in training, but they are also imperative for a highly efficient model. Our primary contributions consist of the following: I) Proposing an extension to the structure risk minimization paradigm of learning, and II) Proving the efficacy of predicates in reducing both the data complexity and the model complexity.

Creating accessible software is imperative for making software inclusive for all users.Unfortunately, the topic of accessibility is frequently excluded from computing education, leading to scenarios where students are unaware of either how to develop accessible software or see the need to create it. To address this challenge, we have created a set of educational labs that are systematically designed to not only inform students about fundamental topics in producing accessible software but also demonstrate its importance. Over the previous year, these labs were included in several Computer Science 2 offerings at the Rochester Institute of Technology, comprising a total of 500 student participants. This article discusses instructional observations from these offerings, some of which include the following: (i) many of the research findings from previous efforts remain true with the larger, more diverse evaluation; (ii) our created material and format reduced students’ belief that creating accessible software was difficult in relation to the baseline,; (iii) we observed that our created material and format benefited student opinion that creating accessible software is important, and (iv) computing majors may not be uniformly impacted by experiential educational accessibility material. The educational labs are publicly available on the project website (https://all.rit.edu).

Multi-armed bandits and contextual multi-armed bandits have demonstrated their proficiency in a variety of application areas. However, these models are highly susceptible to volatility and often exhibit knowledge gaps due to a limited understanding of future states. In this paper, we propose a new bandit framework for what we refer to as informed contextual multi armed bandits (iCMABs) to mitigate these gaps, facilitating "informed" decisions based on predicted future contexts. The performance of an iCMAB is thus highly dependent on the accuracy of the forecast it uses. We examine the use of recurrent neural networks (RNNs) evolved through the EXAMM neuroevolution algorithm as compared to other time series forecasting (TSF) methods and evaluate our iCMAB framework's ability to make stock market trading decisions for the Dow-Jones Index (DJI) in comparison to other decision making strategies using these forecasts. Our results demonstrate that an iCMAB, driven by evolved RNN architectures, performs better than statistical TSF methods, fixed architecture RNNs for TSF, and other CMAB methods. Using evolved RNNs, iCMAB is able to achieve the highest return of over 21%, a similar to 7% improvement over not incorporating forecasted values, and a similar to 5% improvement over DJI's return for that time period.

Research has demonstrated that much of the software being created today is not sufficiently inclusive, unbiased and equitable. This has been found to frequently result in real-world implications such as prejudice against women or people of color, and software that is inaccessible to people with disabilities. Preliminary research has found that empathy-focused experiential educational activities can be beneficial for not only creating empathy, but in advancing the participant's interest and knowledge retention over traditional non empathy-building interventions. This work will provide a foundational background on the current research in the intersection of experiential learning and empathy-building interventions in computing education. We will also present several important questions that still must be explored, thus serving as the foundation for future work in this area.

The Accessible Learning Labs project informs participants on how to properly address web accessibility guidelines, while also demonstrating the need to prioritize accessibility in software development. In this session, an overview of the labs will be provided, along with usage instructions and information for adopters. This tutorial will be beneficial for a wide-range of participants in the software engineering field who would like to gain insight into building inclusive and accessible software. All project material is available on our website: https://all.rit.edu

Although creating accessible software is imperative for making software inclusive for all users, problematically, the topic of accessibility is frequently excluded from computing education. This leads to scenarios where students are not only unaware of how to create accessible software, but also do not see the need to create accessible software. To address this challenge, we have created a set of educational Accessible Learning Labs (ALL) that are systematically designed to not only inform students about fundamental topics in creating accessible software, but also to demonstrate the importance of creating accessible software.

Inequitable software is a common problem. Bias may be caused by developers, or even software users. As a society, it is crucial that we understand and identify the causes and implications of software bias from both users and the software itself. To address the problems of inequitable software, it is essential that we inform and motivate the next generation of software developers regarding bias and its adverse impacts. However, research shows that there is a lack of easily adoptable ethics-focused educational material to support this effort.To address the problem of inequitable software, we created an easily adoptable, self-contained experiential activity that is designed to foster student interest in software ethics, with a specific emphasis on AI/ML bias. This activity involves participants selecting fictitious teammates based solely on their appearance. The participant then experiences bias either against themselves or a teammate by the activity’s fictitious AI. The created lab was then utilized in this study involving 173 real-world users (age 18-51+) to better understand user bias.The primary findings of our study include: I) Participants from minority ethnic groups have stronger feeling regarding being impacted by inequitable software/AI, II) Participants with higher interest in AI/ML have a higher belief for the priority of unbiased software, III) Users do not act in an equitable manner, as avatars with ‘dark’ skin color are less likely to be selected, and IV) Participants from different demographic groups exhibit similar behavior bias. The created experiential lab activity may be executed using only a browser and internet connection, and is publicly available on our project website: https://all.rit.edu.