2026 – Talks & Poster Sessions

Check back on this space after the event for updates about student talks and poster award winners.

Research Day Talks | Research Day Posters

COEIT Research Day Talks 2026

Heparin/Collagen Multilayers Enhance Extracellular Vesicle Production in Human Mesenchymal Stem Cells
Authors: Melanie J. Nelson and Jorge Almodovar (Presenter)
Themes: Bioengineering, Biomimetics, Biosecurity

Extracellular vesicles (EVs) derived from human mesenchymal stem cells (hMSCs) are membrane-bound nano particles (typically less than 200 nanometers in diameter), that play key roles in mediating cell communication and have promising applications in immunotherapy, and tissue engineering. EV research and development is currently limited by the ability to obtain large amounts of EVs with high therapeutic value. Our group has developed a biomimetic cell culture surface, composed of type I collagen and heparin, for hMSC growth. In this work, we demonstrate how hMSCs cultured on our biomimetic surfaces significantly enhance the production of EVs and modulate their cargo. We characterize EV production by determining their concentration via nanoparticle tracking analysis (NPT), their size via transmission electron microscopy and NPT, and their cargo using proteomic analysis. We also evaluated the capacity of the EVs to modulate the behavior of Schwann cells and macrophages. Overall, we confirmed that hMSCs cultured on the collagen/heparin surfaces produce up to three times more EVs compared to culture on tissue culture plastic, that the cargo of the EVs is tuned by the underlying substrate where the hMSCs are cultured, and that these EVs can tune protein expression of macrophages, and Schwan cell migration. This work serves as a platform to obtain large amounts of highly therapeutic EVs for the treatment of deadly diseases.

Leveraging cell-free synthetic biology and protein language models to produce biological polymers
Author: David Garcia (Presenter)
Themes: Bioengineering, Biomimetics, Biosecurity

Cell-free synthetic biology is a powerful tool that enables transcription and translation through cell-free protein synthesis (CFPS), as well as biocatalytic transformations via cell-free metabolic engineering (CFME), using the membrane-free cytoplasmic contents of the cell. By circumventing the constraints of cellular physiology and evolutionary pressures, cell-free systems offer a modular approach to biological transformations, allowing for the rapid characterization of individual biological components with precise control over the chemical environment. These tools redefine how we engineer biological systems for applications in health, materials, and energy. However, the fundamental knowledge and high-throughput techniques necessary to select ideal biocatalysts, reaction conditions, and production platforms are limited. In this talk, I will share work addressing these bottlenecks to improve the function of cell-free synthetic biology towards scalable applications. First, by demonstrating methods to rapidly optimize solid matrix cell-free biosensors; second, by showcasing a framework to scale CFME through a novel co-culturing technique for extract production and the biosynthesis of porphyrin molecules; and third, by integrating cell-free systems with large language models to investigate the substrate scope and promiscuity of biological catalysts and accelerate the production of novel melanin materials.

New strategies for generating hybrid anion-exchange resins for selective treatment of (ultra)short-chain PFAS
Authors: Marylia Duarte Batista, Trevor Gibson, Emily Piazza, Ke He, and Lee Blaney (Presenter)
Themes: Environment and Sustainability

In most water treatment and remediation scenarios, per- and polyfluoroalkyl substances (PFAS) must be concentrated ahead of on- or off-site destruction systems. Current concentration processes favor long-chain PFAS, such as perfluorooctanoate and perfluorooctane sulfonate, over ultrashort-chain PFAS like trifluoroacetate and trifluoromethane sulfonate. To address this gap, we’re developing hybrid anion-exchange (HAIX) resins with enhanced selectivity for short- and ultrashort-chain PFAS. The HAIX resins are generated by depositing metal oxide nanoparticles into commercially available anion-exchange resins. This process is challenging due to Donnan exclusion of polyvalent metal ions in the anion-exchange resins, which contain fixed positive charges. In this presentation, we will share the (1) conceptual framework for selective removal of (ultra)short-chain PFAS by HAIX resins, (2) advanced methods used to produce HAIX resins with different metals, and (3) performance of HAIX resins generated using two primary production protocols for removal of eleven (ultra)short-chain PFAS. The HAIX production strategies involve the use of (i) solvents with low dielectric constants and (ii) low valence metals and in-situ oxidation by permanganate to facilitate incorporation of polyvalent metal ions into anion-exchange resins. With these strategies, we have successfully generated HAIX resins containing iron, manganese, zirconium, copper, zinc, and aluminum. Most HAIX resins exhibited better performance than the corresponding parent resins, with several materials achieving more than 250% greater uptake of trifluoroacetate and/or other (ultra)short-chain PFAS. As a result, we believe that HAIX resins can play a crucial role in addressing ongoing challenges related to treatment and remediation of (ultra)short-chain PFAS.

In vitro assessment of Bicuspid Aortic Valve (BAV) hydrodynamics with varying heart rate
Authors: Nadeem Shah (Presenter), Charles D. Eggleton, and Sayantan Bhattacharya
Themes: Bioengineering, Biomimetics, Biosecurity

The bicuspid aortic valve (BAV), affecting ~2% of the population, predisposes patients to accelerated aortic degeneration and diverse aortopathies. The fused leaflet morphology leads to eccentric jet impingement, elevating the wall shear stress, degrading the aorta wall structure, and increasing the risk of aortic stenosis and aneurysm formation. Current imaging modalities, including 4D flow MRI and echocardiography, have inherent limitations in near-wall resolution, potentially underestimating wall shear stress variability across different BAV phenotypes. While in-vitro hydrodynamic studies using non-invasive methods have characterized flow patterns for common BAV configurations, the hydrodynamic effects of physiological heart rate variations, particularly during exercise conditions, remain unexplored. We present a systematic framework to evaluate how heart rate variation affects BAV outflow hydrodynamics using Particle Image Velocimetry (PIV).

We built a custom resistance-compliance optimized in-vitro mock circulatory loop to mimic the physiological aortic flow conditions. A Masterflex® gear pump was used to generate pulsatile systolic waveforms, capable of delivering peak flow rates up to 100 mL/s. We then simulated exercise conditions by testing the flow at varying heart rates through 60 bpm, 90 bpm and 120 bpm while maintaining a constant cardiac output of 3.82 liters per minute. A bicuspid aortic valve model printed using a Formlabs 4B 3D-printer with flexible Biomed Elastic 50A resin was mounted in the test section.

High-speed Phantom cameras were used to capture synchronized images at 1.1 kHz with a magnification of 20 µm/pixel. To minimize optical distortions, a refractive-index-matched solution composed of water, glycerol, and sodium iodide in a 1:0.3:1.5 ratio was used (refractive index of 1.4741). Image pairs were processed using the open-source Prana software with multipass processing, iterative window deformation, and outlier detection. Preliminary results showed an asymmetric double-jet velocity profile with an intermediate, strong recirculation region. The estimated wall-shear stress is compared for each flow waveform.

Effects of Anisotropy and Defects on Mechanical Performance of Brittle Materials

Authors: Keith Bowman (Presenter), Gizaw Melese, Rokia Elgharably, Daniel Combs, Isaac Poole, Cenia Sims, and Ye Lu

Themes: Manufacturing

The mechanical performance of brittle materials is limited by susceptibility to crack initiation and propagation from flaws. Although significant progress has been made in improving the mechanical performance of ceramic materials over the past three decades, recent demonstrations of crystal plasticity, the development of compositionally complex ceramic alloys with surprising properties, advances in simulation tools, and efforts to broaden the range of ceramic components produced via additive manufacturing provide context for revisiting fundamental assessments of brittle materials. Recent research introducing dislocations into previously considered brittle oxide crystals also offers context for revisiting our understanding of plasticity in ceramics. When combined with the extensive work on so-called high-entropy or compositionally complex ceramics and additive manufacturing of ceramics, revisiting fundamental considerations of how anisotropy and defects interact in new ceramic materials should be of renewed interest. The UMBC Team Ceramics Laboratory, established in 2025, is focused on three primary research themes: 1. Experimental assessments of elastic and plastic anisotropy effects on indentation fracture of ionic and covalent crystalline solids; 2. The effects of flaws resulting from additive manufacturing on fracture of brittle materials; and 3. Simulation of the coupled effects of flaw arrays and anisotropy on fracture initiation and failure of brittle materials. This presentation will share the first results from these three themes produced in our lab.

Acoustic Intelligence for Everyday Healthcare
Author: Dong Li (Presenter)
Themes: Healthcare

Acoustic intelligence is reshaping how everyday technology interacts with human health. Commodity devices such as smartphones, wearables, and earphones are evolving into powerful sensing platforms capable of capturing physiological signals through the human body, enabling continuous, unobtrusive, and scalable health monitoring in real-world settings. This talk presents a vision for transforming everyday devices into intelligent acoustic health sensors for accessible and affordable healthcare. Dr. Dong Li will first highlight his recent work, Acoustoscillogram, which demonstrates that low-cost wired earbuds can detect subtle skin vibrations induced by arterial pulsations, enabling non-invasive cardiovascular monitoring using commodity hardware. He will then introduce his article, From Hearing to Feeling: Unlocking Through-Skin Acoustic Sensing on Smartphones, which explores how smartphones can be transformed into through-skin acoustic sensing platforms for next-generation health applications.

Sensorization, with Care: Community-Driven Smart Technology for Assisted Living
Authors: Tera Reynolds and Roberto Yus (Co-presenters)
Themes: Foundations and Applications of Artificial Intelligence, Human-centered Technology and Accessibility, Software Engineering, Environment and Sustainability, Energy, Physical Systems, Engineering and Technology for Social Good, Community Partnerships and Impact with Engineering and Technology

Assisted living communities (ALCs) are increasingly turning to “”smart”” sensors and connected devices to address challenges such as staffing shortages, resident safety (e.g., fall risk), and care quality. Yet in practice, sensorization is often introduced top-down (i.e., selected for technical capability or cost) without a shared understanding of what residents, staff, administrators, and families actually need, what trade-offs they are willing to accept, or how surveillance concerns may reshape daily life. Building on our community-engaged work in a Baltimore-area nursing home, which surfaced difficulties in communicating sensor options and in balancing tensions among stakeholder priorities, we are developing a scalable, community-driven framework for ethical and effective sensorization in ALCs.

This talk presents our ongoing CIP project and the foundations it lays for a larger research agenda. First, we refine participatory methods for eliciting needs and preferences across diverse ALC populations, including residents with varying levels of physical assistance needs and those in recovery from substance abuse. We combine observations, interviews, and hands-on workshops that use interactive sensor demonstrations and improved communication artifacts. Early evidence suggests that storytelling and personalized, AI-generated visuals can outperform text-heavy explanations, but must be carefully designed to avoid distraction and to reflect context. Second, we describe the development of a structured knowledge base of sensors and devices commonly used in ALCs, integrating technical specifications with privacy-relevant attributes such as hidden costs, communication protocols, and recurring expenses. We use a semi-automated pipeline that combines NLP and generative AI to extract and normalize this information from manufacturer sources for downstream decision support. Finally, we outline our community-building strategy to recruit a diverse network of ALC partners, especially in underserved areas, and to translate stakeholder input into actionable, tailored sensorization plans. We conclude with anticipated deliverables including methodological guidance, an extensible sensor knowledge base, and a roadmap toward proposal-scale deployment studies

Closed-loop Embodied AI Under Physical Constraints for Health and Agriculture
Authors:  Anuradha Ravi (Presenter) and Nirmalya Roy
Themes: Foundations and Applications of Artificial Intelligence, Healthcare, Human-centered Technology and Accessibility, Communications Networks, Energy, Community Partnerships and Impact with Engineering and Technology

This research envisions a unified embodied AI framework that transforms real-world, in-the-wild sensing into reliable, longitudinal decision intelligence under strict physical constraints of computation, energy, and communication. The central idea is that intelligent systems must not only perceive accurately, but also reason and act within bandwidth-limited, resource-constrained environments where sensing, learning, and transmission are co-designed rather than isolated components. We ground this vision in two complementary, high-impact domains: real-time toothbrush monitoring with disease progression prediction, and UAV-based fruit quality assessment in orchards. In oral health, smartwatch-based multimodal sensing (IMU, audio, contextual metadata) will enable continuous modeling of brushing coverage, motion, and force patterns, which are then integrated into personalized longitudinal models to predict plaque accumulation and gingival risk before irreversible damage occurs. In agriculture, UAV-based multimodal perception will convert aerial imagery and contextual signals into fruit maturity trajectories and harvest-readiness forecasts, enabling timely, data-driven decisions. Across both domains, the core innovation lies in a constraint-aware orchestration layer that adaptively balances on-device inference, selective compression, uncertainty-guided transmission, and edge-cloud collaboration to optimize task fidelity under latency, bandwidth, and energy limits. By treating communication and computation as first-class citizens in the learning loop, the proposed framework advances embodied AI from static perception toward closed-loop, resource-aware, decision-centric intelligence. The broader vision is a generalizable paradigm for deploying trustworthy, longitudinal AI systems in health, agriculture, and other physical-world settings where continuous monitoring, early risk prediction, and adaptive sensing must operate robustly despite environmental variability and system-level constraints.

Evaluating the Impact of Pathogen-Mediated Infective Endocarditis on Bioprosthetic Aortic Valve Function
Authors: Corine Jackman Burden and Sayantan Bhattacharya (Co-presenters)
Themes: Healthcare, Bioengineering, Biomimetics, Biosecurity

Infective endocarditis (IE) is a life-threatening condition characterized by bacterial colonization of heart valve tissue, resulting in altered mechanical properties, impaired valve function, and disrupted cardiovascular hydrodynamics. Despite its clinical significance, the mechanistic relationship between bacterial attachment and progressive valve stiffening remains poorly understood, particularly for bioprosthetic valve leaflets. This knowledge gap limits predictive modeling of disease progression and optimization of prosthetic valve design.

In this study, we established a controlled experimental framework to quantify infection-induced changes in leaflet mechanics, kinematics, and flow behavior. A standardized protocol was developed to regulate bacterial adhesion by varying colony-forming units (10⁶–10⁷ CFU), exposure duration (6 and 24 hours), and bacterial strain (Staphylococcus aureus). Fluorescent confocal microscopy was used to quantify percent surface attachment and spatial colonization patterns. Tissue stiffness before and after exposure was assessed using a custom submersible tissue stiffness measurement rig. Initial validation experiments were performed on bovine pericardial tissue, followed by testing on Medtronic bioprosthetic valve leaflets to evaluate clinically relevant behavior. Valve opening and closing kinematics were measured in both healthy and infected states. Statistical comparisons of bacterial adhesion conditions, stiffness changes, and functional metrics were performed across groups. This work provides direct insight into how localized bacterial attachment translates into macroscopic mechanical degradation and altered leaflet dynamics.

Future work will integrate scanning electron microscopy to characterize infection-induced collagen microstructural changes and particle image velocimetry to quantify corresponding alterations in valve hydrodynamics. Together, this platform enables systematic investigation of IE-driven biomechanical remodeling, offering mechanistic insight into valve dysfunction and potentially informing improved diagnostic strategies and prosthetic valve design.

COHERE: Collaborative Optimization of Human Engagement and Robot Effectiveness
Authors: Sruthi Sundharram, Jake Whitt, Golnaz Moharrer, Andrea Kleinsmith (Co-presenter), Charissa Cheah (Co-presenter), Christine Mallinson (Co-presenter), and Ramana Vinjamuri (Co-presenter)
Themes: Foundations and Applications of Artificial Intelligence, Healthcare, Human-centered Technology and Accessibility, Bioengineering, Biomimetics, Biosecurity

COHERE: Collaborative Optimization of Human Engagement and Robot Effectiveness advances human-robot collaboration (HRC) by deriving engineering design principles from human-human teaming and validating them through real-time multimodal robotic systems. Despite rapid advances in robotics, real-world HRC remains limited by challenges in safety, trust, communication, and adaptability. COHERE addresses these barriers by integrating behavioral neuroscience, affective computing, brain-computer interfaces (BCIs), speech interfaces, and robotics within an innovative, classroom-based research and training framework. The project (Aug 2025–July 2026) will implement a three-module special topics course. Module 1 examines human-human collaboration through experiential learning activities while noninvasively recording neural and behavioral signals to characterize cognitive load, affect, and coordination dynamics. Module 2 translates these neurobehavioral insights into actionable engineering principles such as modularity, resilience, adaptability, and multimodal communication to guide collaborative system design. Module 3 applies and evaluates these principles in human-robot interaction tasks.

As a proof-of-concept platform, we have developed a real-time Simulink-based multimodal BCI-robotics system using the g.tec Unicorn EEG headset. Neural signals are streamed and processed in real time to detect motor-related cues (e.g., stomping feet), triggering a virtual robotic arm to grasp a ball. In parallel, a speech-to-text module processes auditory commands (e.g., “happy”) to control a second virtual robotic arm. This dual neural, verbal control architecture enables simultaneous, real-time multimodal interaction and serves as a testbed for studying trust, workload, and collaboration fluency. COHERE will generate annotated multimodal datasets, adaptive control algorithms, and a scalable educational framework, advancing the science of collaborative intelligence and human-centered robotic systems.

A Unified Multiphysics Modeling Framework for Photodetectors
Authors: Ishraq Md Anjum (Presenter), Seyed Ehsan Jamali Mahabadi, Thomas F. Carruthers, Ergun Simsek, and Curtis R. Menyuk
Themes: Physical Systems

High-speed photodetectors serve as critical elements in frequency-comb systems, enabling applications such as precision metrology, coherent optical communications, and low-noise microwave generation. As these systems move toward higher repetition rates and increased optical peak powers, the necessity for robust modeling of ultrafast device dynamics becomes paramount. A primary limiting factor in performance is self-heating, where elevated temperatures degrade carrier mobility.

To optimize computational efficiency in the steady-state analysis, we develop a quasi-one-dimensional (Q1D) thermal framework that exploits the inherent cylindrical symmetry of the Gaussian optical excitation. By focusing on the device’s optical axis and evaluating the radial Laplacian of the temperature field, we rigorously transform the complex three-dimensional lateral heat spreading into a simplified linear relaxation term. This allows the model to account for multi-dimensional heat dissipation without the prohibitive computational cost associated with a full 3D finite-element mesh. A central feature of this framework is the monolithic integration of coupled electro-opto-thermal physical effects. Specifically, the model accounts for the temperature-dependent nonlinearities of critical material parameters, including carrier mobility and diffusion, thermal conductivity, heat capacity, energy bandgap, photon absorption, and effective mass of electrons.

The accuracy of this Q1D electro-opto-thermal approach was validated against experimental measurements of modified uni-traveling-carrier (MUTC) photodetectors. Our results demonstrate that this modeling technique successfully captures the internal temperature distributions, identifying localized thermal peaks near the intrinsic region where Joule heating is most intense. Furthermore, the framework quantifies the impact of self-heating on device performance. This approach provides a computationally robust and physically accurate tool for the thermal management and design of ultrafast optoelectronic systems.

Variational Gibbs State Preparation on Trapped-Ion Devices
Authors: Reece Robertson (Presenter), Mirko Consiglio, Josey Stevens, Emery Doucet, Tony J. G. Apollaro, Sebastian Deffner
Themes: Foundations and Applications of Artificial Intelligence, Quantum Information Science, Quantum Computing, Physical Systems

We implement a variational quantum algorithm for Gibbs state preparation of a transverse-field Ising model on IonQ quantum computers for systems involving 2-4 qubits. We train the variational parameters via classical simulation, and perform state tomography on the quantum devices to evaluate the fidelity of the prepared Gibbs state. We find that fidelity decreases (non-monotonically) as a function of the inverse temperature β of the system. Fidelity also decreases as a function of the size of the system. We find that a Gibbs state prepared for a specified β is a better representative of a Gibbs state prepared for a lower β; or in other words, thermal fluctuations in the quantum hardware increase the temperature of the prepared Gibbs state above what was intended.

AI Agents in Offensive Security
Authors: Sairam Bokka (Presenter) and Keke Chen
Themes: Security and Privacy, Software Engineering

The rise of autonomous AI agents, capable of independent perception, reasoning, and execution, is fundamentally reshaping the cybersecurity threat landscape. This paper argues that a strategic ‘attacker’s advantage’ currently exists, driven by AI’s capacity for scalable offensive operations and the comparatively lower error tolerance required for successful attacks versus reliable defense. Offensive applications have demonstrated significant real-world impact: social engineering incidents increased by 135% following the release of ChatGPT, while AI agents have enabled automated reconnaissance, high-evasion malware generation, and autonomous vulnerability exploitation. To rigorously quantify these capabilities, this study evaluates two specialized benchmarking frameworks: the NYU CTF Dataset, which provides a scalable measure of offensive security performance, and Cybench, which employs subtask-guided evaluation to identify specific failures in agentic reasoning.

Findings confirm that offensive agents currently outperform their defensive counterparts, which remain constrained by limitations in automated remediation and real-world deployment. Nevertheless, expert projections indicate a trajectory toward capability parity within the next decade. This paper concludes that while the short-term landscape favors attackers, the development of coordinated, multi-agent defensive systems is the most promising path toward a resilient long-term security posture.”

Exploring Peer-to-Peer Evaluation with an AI-Supported Learning Tool in an Introductory Programming Course
Authors: Ben Cohen (Presenter), Omobolanle Niyi-Owoeye, Kevin Lemus, Srushti Dharmale, Carine Marette, Patricia Ordóñez, and Edward Dillon
Themes: Foundations and Applications of Artificial Intelligence, Education

With the growing prevalence of generative artificial intelligence and its capacity to instantly generate computational coding solutions through large language model-based queries, concerns have emerged among educators regarding the potential attrition of students’ critical thinking and analytical problem-solving abilities. Existing education literature indicates that peer-to-peer evaluation can function as a pedagogical intervention to promote deeper learning and improve programming performance, particularly among novice programmers. These interventions provide opportunities for students to engage in delivering and receiving constructive feedback, thereby fostering communication skills, reflective thinking, and reinforcement of conceptual understanding in programming contexts. Even in the age of artificial intelligence, new tools are being developed to facilitate peer-to-peer evaluation and support collaborative learning among students.

A case study was conducted in an introductory programming course at a minority-serving institution in the Mid-Atlantic United States during the Fall 2024 semester. The course integrated Kritik360, a commercial-based and AI-supported peer assessment platform, to examine the influence of structured group discussions implemented as weekly learning activities among Information Systems majors in this introductory programming course. The primary objective of this study was to assess the effectiveness of Kritik360 in enabling students to engage in peer-to-peer evaluation within assigned groups as they develop foundational computational thinking skills and understanding core data structures in Java programming. A survey was administered to collect both quantitative and qualitative data regarding students’ perceptions and interactions with the tool. A total of 31 students completed the survey.

The findings indicated that students held moderately positive perceptions of Kritik360’s effectiveness in enhancing their evaluative skills. Additionally, the tool was perceived as beneficial for supporting programming and code comprehension practices. However, when asked about potential areas for improvement, students noted certain aspects of Kritik360’s usability and feature capacity that could be further refined to better support the learning process.

How to write bug-free scientific computing software
Author: Tyler Josephson (Presenter)
Themes: Foundations and Applications of Artificial Intelligence, Software Engineering

When developing new methods for molecular simulation, eliminating bugs can be challenging. Programming languages like Python, FORTRAN, and Julia flag syntax errors, but don’t (and cannot) catch errors in math or program logic – these must be rooted out by human experts. These issues can be managed by following best practices in software development (such as writing tests alongside the program), but even these do not guarantee that code is correct. Probabilistic programs like Monte Carlo are especially notorious.

Lean is a new programming language whose type system enables it to describe and check the logic of advanced math proofs. By translating derivations in science and engineering into math proofs in Lean, we get a computer-checked proof that the derivations are mathematically and logically correct. We can translate derivations in chemistry and engineering into Lean functions and theorems and prove their correctness. We can then write software for scientific computing in Lean, and write proofs about the functions in our execution pipeline, providing guarantees that they have certain properties. We’ve developed formally-verified software in diverse applications, from calculating surface area in porous materials, to computing energies of particles in fluid systems, and translating DNA sequences into their respective amino acid sequences, in each case, merging executable software with formal correctness proofs.

Sequentially Acquiring Concept Knowledge to Guide Continual Learning
Authors: Shivanand Kundargi (Presenter), Kowshik Thopalli, Tejas Gokhale
Themes: Foundations and Applications of Artificial Intelligence

Abstract: The goal of continual learning (CL) in AI is to adapt models to new data (plasticity) while retaining the knowledge acquired from old data (stability). Existing CL methods focus on balancing stability and plasticity to mitigate the challenge of catastrophic forgetting while promoting learning. However, the impact of order and nature of new samples that a model is trained on remains an underexplored factor. A CL algorithm should ideally also have the ability to rank incoming new samples in terms of their relationship with prior data and study their effect on the learning process. Hence in this work, we investigate if scoring and prioritizing incoming data based on their semantic relationships with the model’s current internal knowledge can benefit CL. We propose SACK, short for Sequentially Acquiring Concept Knowledge, a scalable and model-agnostic two-step technique for continual learning. SACK dissects categorical knowledge of the model into fine-grained concepts, computes the relationships between previously learned concepts and new concepts in each experience, and uses this relationship knowledge for prioritizing new samples. Experiments across several types of CL methods (regularization, replay, and prompt-based) in class- incremental and task-incremental settings demonstrate that our approach not only improves accuracy and reduces forgetting in general but also handles long-tail distribution, helps focus on semantically interpretable regions and yields better calibrated continually learned models compared to baseline methods.

COEIT Research Day Posters 2026

Poster abstracts and additional information can be found here.

URCAD Student Demos Highlights

Abstract: With the growing number of entrepreneurs and talented students at the University of Maryland, Baltimore County there is an urgent need for a centralized solution that allows students to advertise and engage in the services/products offered by students within the campus community. Currently, many student entrepreneurs and campus organizations use disconnected communication channels such as social media, word of mouth, or group chats, allowing for limited visibility and inconsistent outreach. As a result, many students on campus aren’t aware of these opportunities and believe they must leave campus to receive the services they need. The Campus Connect is a digital platform which offers a user-friendly website where on-campus student-run businesses can register, create profiles, and promote their products/services directly to the students of UMBC through campus marketplaces and service listings. The Campus Connect addresses the limited visibility and centralized support for student entrepreneurs while reducing barriers for students seeking affordable, convenient, and campus-accessible services. Initial usability testing with nine student participants indicated that users were able to quickly locate services, understand business offerings, and navigate the platform with minimal instruction. These findings suggest that centralized digital marketplaces can significantly improve awareness of campus-based services and reduce accessibility barriers.

Abstract: Created in a Team-Based Game Development class, Mouse House is a game that explores both three-dimensional environments in collaboration with 2D character style developed in the Unity game engine. The game utilizes and explores Unity gravity mechanics and a first-mouse point of view as you maneuver around enemies that can affect the player’s health using mechanics like radial enemies and fright systems through Unity C# Scripts. Playing as a mouse, Mouse House reimagines everyday household objects at a massive scale, transforming ordinary spaces into immersive and dynamic environments. A 3D environment was constructed with Autodesk Maya to provide an intricate world full of ample hiding spaces, and player interface and 2D assets were created in Krita and edited in Adobe Animate to create a hand-drawn sense of whimsy to contrast the large and harsh environment the player must maneuver. Development of this game provided for a uniquely engaging collaborative experience that allowed for cross-discipline exploration of programming, visual design, and overcoming challenges in a team-based setting.

Research Day Posters

  • 1
    Authors: Mohammad Saeid Anwar, Anuradha Ravi, Emon Dey, Gaurav Shinde, Indrajeet Ghosh, Jade Freeman, Carl Busart, André Harrison, Nirmalya Roy
    Title: CoOpTex: Multimodal Cooperative Perception and Task Execution in Time-critical Distributed Autonomous system
  • 19
    Authors: Molly E. Balkan, Shanmukhi Gundu, Sudip Chakraborty, Maloy K. Devnath, Vandana P. Janeja
    Title: Graph-based detection of spatial linkages between sea ice retreat and ice shelf melting over the polar regions.
  • 2
    Authors: Mostafa Cham, Bayu Adhi Tama, Cheng Gong, Mathieu Morlighem, Jianwu Wang
    Title: LLM-SR-UQ: Uncertainty-Aware LLM-Guided Symbolic Regression
  • 3
    Authors: Yash Diggikar (presenter), Milton Halem
    Title: A Machine Learning OSSE Framework for Satellite Observations A Multi-Model Study: FourCastNet, Aurora, and GraphCast
  • 4
    Authors: Muhammad Hasan Ferdous (presenter), Md Osman Gani (faculty mentor)
    Title: G-DCD: Generalized Decomposition-based Causal Discovery for Multivariate Multi-Seasonal Temporal Data
  • 5
    Authors: Md Badrul Hasan (Presenter – Ph.D. Candidate), Meilin Yu, Tim Oates
    Title: Machine Learning-Enhanced Turbulence Modeling for Hurricane Boundary Layer Simulations
  • 8
    Authors: Uzma Hasan (presenter), Dr. Md Osman Gani
    Title: Uncertainty Quantification for Learned Causal Graphs through Heterogeneous Evidence Fusion
  • 20
    Authors: Muhammad Behroze Hassan, Bayu Adhi Tama, Sanjay Purushotham, Vandana P. Janeja
    Title: XCheck: A Consistency-Based Validation Framework for Englacial Layers Annotations
  • 9
    Authors: Jumman Hossain and Nirmalya Roy
    Title: QPRL: Learning Optimal Policies with Quasi-Potential Functions for Asymmetric Traversal
  • 15
    Authors: Oluwatobiloba Odunsı, Aravind Mohan, Seraj Al Mahmud Mostafa, Jianwu Wang
    Title: CloudBot: Autonomous End-to-End Cloud Deployment from Code to Infrastructure
  • 10
    Authors: Sourajit Saha (presenter), Tejas Gokhale
    Title: Zero-Shot Multimodal Retrieval with Multi-Scale Contextual Representations
  • 16
    Authors: Md Sakib Ul Rahman Sourove (presenter), Lujie K. Chen and Shimei Pan
    Title: An LLM-Based Agentic AI System for Automated Construction of Knowledge Taxonomies in Data Science Problem Solving
  • 11
    Authors: Tartela Tabassum (Presenter), Roy Prouty, Elliot Gobbert, Jianwu Wang
    Title: LLM-driven user support for high-performance computing resources
  • 12
    Authors: Zahid Hassan Tushar (presenter); Sanjay Purushotham
    Title: HyperFM: An Efficient Hyperspectral Foundation Model with Spectral Grouping
  • 42
    Authors: Dr. David Garcia, Camille Basden (proposed presenter)
    Title: Paper-Based Cell-Free Systems
  • 30
    Authors: Rebecca Boese (Presenter) and Dr. Corine Jackman Burden
    Title: Investigating mechanisms mediating pathogen adhesion in infective endocarditis using aortic bovine valves.
  • 31
    Authors: Sudarshan Bollapragada (Presenter), Corine Jackman Burden
    Title: Microbiome Regulation of Cervical Cancer Progression
  • 32
    Authors: Damilola Fapohunda (Presenter), David Garcia
    Title: Measuring pH and Metabolite Changes in Cell Free Systems Using Fluorescent Biosensors
  • 43
    Authors: Neveen Faris ( presenter), Rishika Bandi, Lexi Malenfant, Maya Sanyal, Riya Koshy, Vikash Kumar, Mike Tolosa, Venkatesh Srinivasan (mentor), Govind Rao
    Title: Breathable Shake Flask Platforms for High-Yield Recombinant Protein Manufacturing
  • 44
    Authors: Lucas Gois (Presenter), Hanlu Yang, Trung Vu, Erdem Kumbasar, Denis Fantinato, Aline Neves, Vince D. Calhoun, and Tülay Adali
    Title: Domain-Informed Independent Vector Analysis for multisubject fMRI analysis
  • 33
    Authors: Maya Haywood (Presenter), David Garcia
    Title: Leveraging Protein Language Models and Cell-Free Protein Synthesis to Identify Effective Divalent Metal Cofactor–Polyphenol Oxidase Pairings for Optimal Catalytic Activity
  • 34
    Authors: Emily H. Kruszon (presenter), Sayantan Bhattacharya, Charles D. Eggleton
    Title: Measurement of shear stresses on the coupon surface as a function of RPM in a CDC Biofilm reactor
  • 35
    Authors: Shayan Manuchehrfar, Molly Y. Mollica
    Title: Heterogeneity in Single-Platelet Force Generation
  • 39
    Authors: Katelyn Prasad (presenter), Nadeem Shah, Sayantan Bhattacharya, Corine Jackman Burden
    Title: Design and Validation of a Submersible Mechanical Testing System for Aortic Valve Leaflet Stiffness Characterization
  • 36
    Authors: Matthew S. Quintanilla, Ololade D. Lawrence, Ethan F. Folmer, Jayne M. Zeller, Alexander G. Doan, Kelsey Gray, Athira Anilkumar, Nachammai Napiappan, Deepa Madan, Joseph Washington, Mark R. Marten
    Title: Determining the Impact of Dual Approaches on the Mechanical Strength of Mycelial Materials
  • 40
    Authors: Sina Razaghi (presenter), Mehdi Kiani
    Title: MagSonic: A Hybrid Magnetic–Ultrasonic Wireless Interface for Next-Generation Miniaturized Biomedical Implants
  • 41
    Authors: Nazanin Saberi, Molly Y. Mollica
    Title: Distinct platelet traction forces and morphology on fibrin scaffolds compared to planar fibrinogen
  • 23
    Authors: Md Biplob Hosen {presenter}, Houbing Herbert Song , Shuling Yang and Lujie Karen Chen
    Title: NeuroSymRead: Symbolic Governance of Neural Generation for Adaptive Dialogic Reading
  • 24
    Authors: Vasundhara Joshi, Vasundhara Joshi (presenter), Surely Akiri, Sanaz Taherzadeh, Gary Williams, Andrea Kleinsmith
    Title: Investigating differences in Paramedic trainees’ multimodal interaction during low and high physiological synchrony
  • 112
    Authors: Ravi Kuber, Patti Ordonez, Marjory Pineda, Foad Hamidi, Marilyn Iriarte Santacruz.
    Title: Towards Identifying Best Practices for Accessible Makerspace Design
  • 113
    Authors: Marilyn P. Iriarte
    Title: Engaging Underserved Communities in Computing
  • 25
    Authors: Kevin Lemus, Christian Ruiz, Stephanie J. Lunn, and Edward Dillon
    Title: Cultura Connections: Harnessing Large Language Models to Establish Examples of Data Structures Relevant for Hispanic and Latine Students
  • 115
    Authors: Maria M. Lopez-Delgado [presenter], Dr. Ravi Kuber
    Title: Co-designing with Early Childhood Educators for Inclusive Computational Thinking and Creative Technologies Lessons in Puerto Rico
  • 26
    Authors: Omobolanle Niyi-Owoeye, Uzma Hasan, Kevin Lemu, Srushti Dharmale, William Parham, and Edward Dillon
    Title: Fostering Comprehension in Introductory Programming through Code Reviews and Verbal Explanations in the Age of Generative AI
  • 27
    Authors: William Parham III, Olivier Woodgett, Martita Perez, Patrina Pun, Kevin Lemus, and Edward Dillon
    Title: Using Generative AI to Examine Cultural References for Understanding Computational Data Structures
  • 116
    Authors: Alan T. Sherman, Bharg Barot, Enis Golaszewski Cyber Defense Lab, Computer Science Department, Maria Sanchez Engineering and Computing Education Program, UMBC, inda Oliva Education Department, UMBC, Peter Peterson Computer Science Department, University of Minnesota Duluth
    Title: Introductory Engineering Education
  • 28
    Authors: Sadia Nasrin Tisha, Md Nazmus Sakib, Rebecca Williams, Karen Chen, Sanorita Dey
    Title: Towards AI-facilitated Collaborative Visual Sensemaking
  • 114
    Authors: Mei-Lian Vader, Krystal Zhang, Grace Hollen, Emily Wingeart (Presenter), Foad Hamidi, Ravi Kuber
    Title: Investigating the Impact of a 3D Modeling and Printing Workshop Designed for Blind and Low-Vision Students
  • 111
    Authors: Chaturya Yarradoddi, Anupam Joshi
    Title: WIP: The Impact of Financial Aid and Academic Pathways on Student Success: Analytics, Predictive Modeling, and Interactive Tools
  • 37
    Authors: Sanzida Akter*, Lida Xu, Mahmoud Jalali Mehrabad, Mohammad Hafezi, Curtis R. Menyuk
    Title: Chaos Diagnostics in Topological Super-Ring Kerr Microcombs via Lyapunov Exponents
  • 60
    Authors: Logan Courtright, Alioune Niang, Peter Hedlesky, Patrick O’Mullan, Ergun Simsek, Gary Carter, James Eakin, Tanvir Mahmood, James P. Cahill, Weimin Zhou, Doug Petkie, Curtis R. Menyuk
    Title: Design and Characterization of Thick Silicon Nitride Microresonators from AIM Photonics
  • 38
    Authors: Zachary Danielson (presenting author), Pradyoth Shandilya, Kartik Srinivasan, Gregory Moille, and Curtis R. Menyuk
    Title: Calculating the Route to Chaos of Dissipative Kerr Solitons Driven by a Modulated Laser
  • 59
    Authors: Alexander Dorsey, Ankit Goel
    Title: Experimental Validation of Dynamic Mode Adaptive Control on Multi Rotor Platform
  • 45
    Authors: Raonaqul Islam, (Presenter); Pradyoth Shandilya, Curtis Menyuk, Ergun Simsek
    Title: Self-trapping of dissipative Kerr solitons for low-noise frequency combs
  • 46
    Authors: Revati Kadolkar (Presenter), Govind Rao, Douglas D. Frey
    Title: Application of Mechanistic Modeling for the Development of a Miniaturized Size Exclusion Chromatography (SEC) Column for on-site Quantitative Analysis
  • 47
    Authors: Benjamin Kale, Meilin Yu
    Title: Simulations of turbulent hydrocarbon fuel injection and combustion in a cavity-based scramjet
  • 48
    Authors: Parham Oveissi, (Presenter); Turibius Rozario, Ankit Goel
    Title: A Novel Neural Filter to Improve Accuracy of Neural Network Models of Dynamic Systems
  • 49
    Authors: Soumik Sarker (Presenter), Alok Ghanekar
    Title: Slow-Light-Inspired Steering of Directional Thermal Radiation with Phase-change Materials
  • 50
    Authors: Nahidul Islam Shadin (Presenter), Raymond Yu, Dr. Michelle L. Povinelli, Dr. Alok Ghanekar
    Title: Reversible Symmetry Breaking of Directional Thermal Emission in VO₂–SRO Gratings
  • 51
    Authors: Pradyoth Shandilya (presenter), Gregory Moille, Giuseppe D’Aguanno, Kartik Srinivasan, and Curtis R. Menyuk
    Title: A study of dual-pumped microresonators using three-wave equations
  • 52
    Authors: Gaurav Shinde (Presenter), Anuradha Ravi, Jared Lewis, Andre Harrison , Henry Gardiner, Md Saeid Anwar, Shadman Sakib, Jade Freeman, Nirmalya Roy
    Title: CAViAR: Quality-Aware Vision-and-Radio Fusion for Relative Range Estimation among Collaborative Autonomous Agents
  • 58
    Authors: Paris von Lockette
    Title: The Electro-Magnetically Active Composites and Structures (eMACS) Lab at UMBC
  • 55
    Authors: Liam Wilson (Presenter) and Meilin Yu
    Title: Wake-type Gust Mitigation with Airfoil Pitch Motion
  • 56
    Authors: Monty Yates (Presenter), Reece Robertson
    Title: Fluids on the Bloch Sphere: Quantum Algorithms for Solving PDEs on NISQ
  • 57
    Authors: Cindy Z.A. Almeida (Presenter), John T. Hrynuk, Meilin Yu
    Title: SPOD reconstruction analysis on transitional flow applied to wing-gust interactions
  • 53
    Authors: Amir Babaei-Gharehbagh (Presenter), Jemma Przybocki, Marissa Cuevas, Isaiah Smith, Maria A.Zawadowicz, Akua Asa-Awuku, Benjamin A. Nault, Peter F. DeCarlo, Christopher J. Hennigan
    Title: Urban-Rural Gradients in Aerosol Liquid Water and pH during the CoURAGE Campaign
  • 54
    Authors: Emam Hossain (Presenter), Md Osman Gani
    Title: Refining Partial Causal Graphs Through Interventional Representation Learning
  • 63
    Authors: Nathalie J. Lombard (presenter), Trevor P. Needham, Hilda Khoei Fadaei, Rebecca Donovan, Joel Baker, Upal Ghosh
    Title: Using historical datasets on fish consumption advisory to assess management action effectiveness
  • 64
    Authors: Robert Schroeder (Presenter), Md Badrul Hasan, Dr. Meilin Yu
    Title: Data-Driven Modeling of Dynamic Stall in Vertical-Axis Wind Turbines
  • 61
    Authors: Sirisha, Milton Halem
    Title: Towarda an advanced AI fire Forecast model
  • 62
    Authors: Dingxiang Zhu (Presenter); Ye Lu
    Title: A Novel Digital Image Correlation Framework for Structural Health Monitoring
  • 77
    Authors: Sultan Ahmed, Sanjay Purushotham
    Title: FSA-Bench: Large-Scale Benchmarking of Survival Models in Federated and Heterogeneous Settings
  • 78
    Authors: Wanqing Chen (Presenter), Kai Sun
    Title: Predict-Then-Optimize for Large-Scale Anesthesiologist Scheduling with LLM-Enhanced Availability Prediction
  • 79
    Authors: Ommo Clark (presenter); Karuna Pande Joshi
    Title: The Online Health Safety Gap: VERITAS — A Neuro-Symbolic Framework for Risk-Aware Credibility Assessment in Online Health Discourse Beyond Misinformation Detection
  • 89
    Authors: Weiding Fan, Sanjay Purushotham
    Title: Worst-Client-Aware Federated Structure Learning for Multi-Environment Time Series
  • 80
    Authors: Safayat Bin Hakim (Presenter), Aniqa Afzal, Qi Zhao, Houbing Herbert Song
    Title: CyberCane: Neuro-Symbolic, Ontology-Guided RAG for Trustworthy Phishing Detection in Healthcare and Beyond
  • 81
    Authors: Tasnim Nishat Islam, Mohamed Younis, Wassila Lalouani, Lloyd Emokpae, Roland Emokpae Jr
    Title: Breathing Cycle Detection for Respiratory Tele-health Systems
  • 82
    Authors: Urvi Jain (Presenter), Cynthia Chikomoni (Presenter), Dr. Corine Jackman Burden (Faculty Mentor)
    Title: Investigating the Role of Pneumococcal Phenotypic Heterogeneity in Determining Virulence Severity
  • 90
    Authors: Yiming Liao, Keke Chen (presenter and faculty mentor)
    Title: Med-HEAL: Analyzing and Healing Hallucinations in Medical LLMs through ICL
  • 83
    Authors: Alyssa N. Maguina (presenter), Sithumina Weerarathna, Rishav Gupta. Faculty Mentors: Dr. Janelle Clark and Dr. Dong Li
    Title: Integrating Psychophysics, Tissue Mechanics and Smartphone Ultrasound for Personalized Human-Robot Interaction
  • 84
    Authors: Milind Rampure (Presenter). Faculty Mentor/Advisor: Dr. Nirmalya Roy. Co-Advisors: Dr. Anuradha Ravi, Dr. Zahid Hasan
    Title: Robust Human Perception for Search and Rescue Robotics: From Underwater Identification to Contactless Vital Assessment
  • 92
    Authors: Pavan Raj Ravi, Dr.Kai Sun, Dr.Jianwu Wang
    Title: A Ground-Truth Structural Causal Simulator for Nursing well-being Analytics
  • 86
    Authors: Jason Rojas (Presenter), Jiajie He, Yash Patel, Yuechun Gu, Zeyun Yu, and Keke Chen (Faculty Mentor)
    Title: Secure-by-Disguise: Clinical Validation of DisguisedNets for Confidential Medical Imaging
  • 87
    Authors: Shadman Sakib (Presenter), Gaurav Shinde, Nirmalya Roy
    Title: Decoupling Perception and Reasoning for Contactless Respiratory Rate with Vision Language and Small Language Models
  • 88
    Authors: Presenter), Khaled Solaima
    Title: Benchmarking Early Deterioration Prediction Across Hospital-Rich and MCI-Like Emergency Triage Under Constrained Sensing
  • 91
    Authors: Zafira Wasma (Presenter), Emam Hossain, Md Osman Gani
    Title: Evaluating Causal and Machine Learning Models for Type 2 Diabetes Risk Prediction
  • 66
    Authors: Brandon Ables, Dr. Andrea Kleinsmith
    Title: Exploring Embodied Personal Knowledge Management as Systemic Interactivity
  • 67
    Authors: Saquib Ahmed (presenter), Tejo Gayathri Busireddy, Sanorita Dey
    Title: Enhancing Image Comprehension: The Impact of AI-Generated Explanations on Perception of Altered and Synthetic Media
  • 68
    Authors: Zainab Balogun, Bella Dongarra, Samon Nguyen, Candace Gyimah, and Tera Reynolds
    Title: A Human-centered Design Approach for Supporting Self-management of Hypertonic Chronic Pelvic Pain Syndrome
  • 69
    Authors: Rishav Gupta, Dr Dong Li
    Title: Enabling Affordable and Accessible Blood Pressure Monitoring on Smartphones
  • 70
    Authors: ASM MOBARAK HOSSAIN
    Title: A Multi-Modal Agentic Framework for Auditing Wheelchair Accessibility
  • 71
    Authors: Md Alomgeer Hussein (Presenter); Rushali Sreedhar; Yachi Jitendrabhai Patel; Sanika Bishnoi; Samon Nguyen; Tera Reynolds
    Title: Understanding the Perceptions of People from Underserved Communities around Generative Artificial Intelligence for Health Information Work
  • 72
    Authors: Kodilinye Mkpasi (Presenter); Corey Benjamin; Dong Li; Anuradha Ravi; Nirmalya Roy; Mary Beth Aichelmann-Reidy
    Title: “O-HygieCare”: Predictive Oral Health Monitoring through Longitudinal Toothbrushing Analytics using Smart Wearable Intelligence
  • 73
    Authors: Golnaz Moharrer (Presenter) , Krystal Zhang, Andrea Kleinsmith
    Title: Making Without Purpose, Growing With Intention: Embodied Creative Reflection for Emotional Resilience in Graduate Students
  • 74
    Authors: Qi Zhao, Marjory Pineda, Ketul Kishorbhai Chhaya, Yasmine Kotturi
    Title: AI Literacy in Context: Exploring What AI Literacy Means for Entrepreneurs
  • 75
    Authors: Kavya Rajendran (Presenter), Dr. Andrea Kleinsmith
    Title: The Emotional Side of Reading News through Social Media for International Students in the US
  • 65
    Authors: Sruthi Sundharram (Presenter), Jake Whitt, Golnaz Moharrer, Andrea Kleinsmith, Charissa Cheah, Christine Mallinson, Ramana Vinjamuri
    Title: COHERE: Collaborative Optimization of Human Engagement and Robot Effectiveness
  • 76
    Authors: Krystal Zhang (presenter); Marie Sakowicz; Emily Wingeart; Faculty mentor: Foad Hamidi
    Title: Belonging in the Making: Investigating Inclusive Makerspace Design for Youth with Autism
  • 103
    Authors: Bahirah Adewunmi (Presenter), Sanjay Purushotham
    Title: TIE Grammar: Stratified Generative Pipeline for Training Generalizable Deep Reinforcement Learning Cyber Agents
  • 104
    Authors: Bahirah Adewunmi (Presenter), Ed Raff, Sanjay Purushotham
    Title: SubstratumGraphEnv: Reinforcement Learning Environment (RLE) for Modeling System Attack Path
  • 105
    Authors: Zeliatu Ahmed (Presenter), Faculty Mentor: Dr. Karuna Pande Joshi
    Title: Ontology Driven Agentic System for Automating Security Compliance in Medical Cyber-Physical WBANs
  • 18
    Authors: Jalen Brown, Pearce Packman, Roberto Yus
    Title: Privacy-Preserving Indoor Navigation for the UMBC TRC Building
  • 106
    Authors: Deontic Knowledge Graphs for Privacy Compliance in Multimodal Disaster Data Sharing
    Title: Presenter: Kelvin Uzoma Echenim, Faculty Mentor: Karuna Pande Joshi
  • 108
    Authors: Yuechun Gu, Jiajie He, Keke Chen
    Title: Auditing Approximate Machine Unlearning for Differentially Private Models
  • 109
    Authors: Jiajie He, Min-chun Chen, Xintong Chen, Xinyang Fang, Yuechun Gu, Keke Chen
    Title: ICL-RecSys Privacy Risk
  • 22
    Authors: Dharani Nadendla, Renzhi Hao, Shirui Cao, Yizhu Wen, Rishav Gupta, Mehran Kafai, Hanqing Guo, Dong Li
    Title: Ultrasound Watermark: Real-time Acoustic Watermarking for Voice Scam Protection on Smartphones
  • 107
    Authors: Hadjar Ould Slimane (presenter), Mohamed Younis, Yousef Ebrahimi
    Title: AI-based Traffic Analysis Attack Mechanism for IoT Systems
  • 110
    Authors: Sejal Patil (presenter), Reece Robertson, Sebastian Deffner
    Title: Secure Quantum Handshakes: Simon’s Algorithm for Quantum Network Verification
  • 6
    Authors: Shaswati Saha, Sourajit Saha, Manas Gaur, Tejas Gokhale
    Title: Side Effects of Erasing Concepts from Diffusion Models
  • 21
    Authors: Gaurav Sharma, Milton Halem, Yaacov Yesha
    Title: A Digital Twin for the Safety of Smart Ports
  • 7
    Authors: Javed Tamboli, Karuna Joshi
    Title: Security Compliance for Smart Manufacturing using Knowledgegraph based Digital Twin
  • 13
    Authors: Wenkai Tan, Jayaprakash B. Shivakumar, Rishikesh S. Govindarajan, Nicholas Reed, Daewon Kim, Eduardo Rojas, Yongxin Liu, Huihui Wang, Houbing Song
    Title: Anomaly Detection for Additive Manufacturing with Antenna-Based Embedding Sensors: An Explainable, Instructive Learning Framework
  • 14
    Authors: Zahid Hassan Tushar (presenter); Sanjay Purushotham
    Title: Security of Biomedical Large Language Models: Threats, Defenses, and Open Challenges
  • 17
    Authors: Afia Zuhaira (Presenter) , Mohamed Younis
    Title: PUF-Based Reconfigurable QAM Modulation for Secure Communication
  • 99
    Authors: Mst Maksuda Bilkis Baby (Presenter), Khushika Shah, Naiyue Liang Emma, Faculty Mentor: Lei Zhang
    Title: Separating Secrets from Placeholders: A Hybrid CNN-CodeBERT Framework for Three-Class Credential Leakage Detection
  • 98
    Authors: Venkat Ganapathy, Samin Semsar, Evelyn Kempe, Aaron Massey, Sai Nikhil Reddy Pendhyala, Carolyn Seaman, Sreedevi Sampath
    Title: Managing regulatory ambiguities within SDLC
  • 97
    Authors: Ainaz Jamshidi (Presenter), Dongchan Kim, Lei Zhang
    Title: From Vulnerabilities to Weaknesses: A Retrieval-Based Siamese Transformer Approach
  • 96
    Authors: Dr. Muhammad Ali Yousuf, Anjali Jha
    Title: A-Eye: Empowering Independence in Individuals with Color Vision Deficiency through Generative AI-Assisted Dietary and Daily Navigation
  • 93
    Authors: Peiying Liu (Department of Diagnostic Radiology & Nuclear Medicine, University of Maryland School of Medicine, Baltimore, Maryland, USA); Elham Karimigharighi (Department of Diagnostic Radiology & Nuclear Medicine, University of Maryland School of Medicine, Baltimore, Maryland, USA and Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, Baltimore, Maryland, USA); Hanzhang Lu (Department of Radiology, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA); Fariba Badrzadeh (Department of Diagnostic Radiology & Nuclear Medicine, University of Maryland School of Medicine, Baltimore, Maryland, USA)
    Title: Normalized cerebrovascular reactivity mapping using hypercapnia and hyperoxia challenges
  • 94
    Authors: Jamel Lawson – Presenter, Dr. Sreedevi Sampath
    Title: Vibe Coding and Software Quality Assurance: A Systematic Mapping Study
  • 100
    Authors: Joey Mule (PRESENTER), Shahmir Rizvi, Tejas Gokhale, Riadul Islam
    Title: STOP-ET: Spatio-Temporal Optical Pipeline for Event-based Threats
  • 95
    Authors: Dr.Carolyn Seaman (Faculty mentor) and Mahsa Radnead (Presenter)
    Title: Explainable AI for Identifying and Managing Test Debt
  • 101
    Authors: Hasan Masum, Mehreen Rashid (Presenter), Tarannum Shaila Zaman
    Title: Evaluating Large Language Models for End-to-End System-Level Concurrency Bug Reproduction
  • 102
    Authors: Christian Wilkins (Presenter), Dong Li , Rishav Gupta
    Title: Smartphone Human Detection using Acoustic Sensing