Offered Tutorials/Workshops

Offered Tutorials/Workshops

The following tutorials/workshops are offered for ACMSE 2026:


Visual Question Answering and RAG Using Generative AI

Presenter: Gourav Bathla (GLA University – India)
Type of Event: Workshop
Date: Thursday, April 23, 2026
Time: 09:30-11:30 (Central Time)
Duration: 2 hours
Room: Room 154

Abstract:
Visual Question Answering (VQA) is a multimodal learning task that aims to generate accurate answers to natural language questions based on visual content such as images or videos. The questions may require binary (yes/no) responses, object counting, attribute recognition, spatial reasoning, or detailed descriptive understanding of specific objects or scenes within the visual input. Traditional VQA approaches typically rely on convolutional neural networks (CNNs) or pre-trained visual backbones such as VGGNet and ResNet for feature extraction from images, combined with sequence-based language models like Long Short-Term Memory (LSTM) networks to encode textual questions. These visual and textual representations are then fused using techniques such as concatenation, attention mechanisms, or multimodal embeddings to predict the final answer. While such architectures provide reasonable performance on standard VQA benchmarks, their capability to capture complex contextual relationships and high-level semantic reasoning remains limited. Recent advancements in Large Vision Models (VLMs), including Vision Transformers (ViTs) and foundation models such as Gemini, have significantly improved VQA performance. These models leverage transformer-based architectures, large-scale pretraining on multimodal datasets, and self-attention mechanisms to model long-range dependencies and fine-grained interactions between visual and textual modalities. As a result, they demonstrate superior performance on complex and real-world VQA datasets involving compositional reasoning, scene understanding, and open-ended queries. In this workshop, VQA will be demonstrated using both traditional deep learning architectures and state-of-the-art Large Vision Models. Participants will gain practical insights into model architectures, multimodal feature fusion strategies, training pipelines, and performance comparisons, highlighting the evolution of VQA systems from classical neural networks to modern large-scale vision-language models.

Keywords:
Visual Question Answering (VQA), Large Vision Model (VLM).

Covered Topics:
The covered topics include:

  • Questions and image embeddings
  • Iimplementation using ResNet and LSTM
  • Demonstration of VQA using Gemini
  • ViT (Vision Transformer)
  • RAG (Retrieval-Augmented Generation)

Prerequisites for Participants:
Machine Learning, Neural Networks, Python.


An Introduction to Embedded Systems Programming

Presenter: Jay Snellen (Jacksonville State University – USA)
Type of Event: Tutorial
Date: Thursday, April 23, 2026
Time: 14:00-17:15 (Central Time)
Duration: 3 hours
Room: Room 154

Abstract:
“Embedded systems” are small, highly efficient computers that are built into another device and are typically dedicated to controlling or monitoring the device. The operation of the embedded system is so tightly integrated with the device that, from the user’s point of view, the computer cannot be considered in isolation; the correct functioning of the embedded system is synonymous with the correct functioning of the device.

The design and programming of embedded systems is a fruitful area of exploration, for hobbyists and for students of Computer Science alike, but it also entails several unique challenges. Memory and processing power are often severely limited, and because embedded systems must provide uninterrupted long-term operation with little to no hands-on maintenance or intervention, correctness and predictability are essential. These challenges can add to one’s appreciation of the skills required, and acquiring those skills can also enlighten one’s exploration of more conventional computers. Since most computers in the world are embedded systems, relied upon by an increasing number of occupations, the exploration of embedded systems is also a worthwhile career investment. It is also an exciting and engaging way to learn about the fundamentals of computer architecture and good programming practices, while solving a range of interesting problems and working hands-on with an interesting range of platforms.

This tutorial introduces the fundamental concepts and ideals of embedded systems. After establishing the necessary background, it will proceed to introduce embedded systems programming through a variety of hands-on exercises with major embedded system platforms. It will begin with small-scale embedded systems based on microcontrollers, and their respective development tools. The microcontroller platforms introduced will be the MCS-51 family of microcontrollers, which have long been widely used in educational applications, as well as the Arduino, a popular family of consumer-oriented microcontroller kits. It will conclude with an introduction to single-board computers, with an emphasis on the Raspberry Pi.

Keywords:
Embedded Systems, C, Firmware, Microcontrollers, Single-Board Computers, MCS-51, 8051, AVR, Arduino, Raspberry Pi, Linux

Covered Topics:
The covered topics include:

  • The concepts and ideals of embedded systems
  • The role of cross-compilers, cross-assemblers, and linkers
  • Using Integrated Development Environments (IDEs) for embedded systems
  • The workflow of compiling and downloading firmware for embedded systems
  • Embedded systems monitoring and troubleshooting using in-circuit debugging
  • Communication for embedded systems, including serial and network communications

Prerequisites for Participants:
Ideally, the audience should have a basic knowledge of programming languages such as C and Python.


Broadening CI Workforce Development for Quantum-Based Machine Learning Research in Science and Engineering

Presenter: Dan Lo and Yong Shi (Kennesaw State University – USA)
Type of Event: Workshop
Date: Saturday, April 25, 2026
Time: 08:45-12:00 (Central Time)
Duration: 3 hours
Room: Room 154

Abstract:
Quantum computing and artificial intelligence are rapidly advancing with the potential to transform science, engineering, and industry. However, developing a skilled workforce capable of integrating quantum principles with modern machine learning techniques remains a significant challenge. Current educational resources often lack accessible, hands-on learning materials that bridge the gap between abstract quantum mechanics and practical algorithm implementation. As an increasing number of scientific and engineering (S&E) disciplines seek to leverage quantum machine learning (QML) to accelerate discovery and innovation, there is a growing need for a community-driven, unified training program that enables researchers to acquire advanced knowledge and skills in QML. This workshop will get you started in learning our developed materials.

To address these challenges, we launched the QML Pilot CyberTraining program in 2024–2025. The program successfully met its goals in recruitment, participation, training delivery, dissemination, curriculum development, research productivity, and evaluation. The goal of this proposed CyberTraining program, HOT-QML-SE, is to expand and scale an innovative hands-on QML CyberTraining program across multiple universities in a broader disciplinary range of S&E, building upon the successful outcomes of our prior Pilot program. This project will develop a scalable and sustainable online hands-on CyberTraining platform supporting open access, self-paced, or instructor-guided QML learning experiences. The open-source learning modules developed in this project will explore QML in various S&E fields, including computer science, civil and environmental engineering, industrial engineering, physics, and related disciplines. This project will host multi-faceted training events annually, including faculty development workshops, student learning camps, and conference tutorial sessions. The project will be deployed on an open public website, and all learning modules will be integrated into curricula across S&E disciplines, as well as all the training events, for sustainable QML CyberTraining.

This project addresses the national need for a workforce skilled in emerging quantum and AI technologies by integrating QML training into S&E education. This project proposes a scalable and sustainable hands-on learning model for integrating emerging QML concepts into traditional S&E curricula. The project will make its innovative contribution on (1) easy adoptable and deployable, scalable, hands-on QML learning modules, (2) multi-faceted training events for both S&E faculty and students, (3) sustainable curriculum integration in S&E, and (4) an open educational resource (OER) repository and a book publication ensuring long-term sustainability. The project will work closely with a community involved in QML and S&E research, be guided by an External Advisory Board, and be evaluated by an independent external evaluator. Continuous improvements will be guided by feedback from both stakeholders and participants.

This project will significantly advance research, education, and workforce development in QML across Georgia, Alabama, and Florida through a coordinated multi-state and multi-institutional collaboration. By leveraging complementary expertise and shared infrastructure among computer science, civil and environmental engineering, industrial engineering, and physics programs, the initiative will foster a vibrant interdisciplinary ecosystem that facilitates cross-pollination of ideas and methods. The project will expand access to cutting-edge research experiences, industry-aligned training, and hands-on learning opportunities for students from diverse backgrounds, thereby strengthening the S&E pipeline in the Southeastern region. Anticipated impacts include enhanced research productivity, accelerated technological innovation, expanded academic–industry partnerships, and increased representation in emerging quantum-related fields. Additionally, the initiative’s collaborative and scalable framework is designed to persist beyond the funding period through sustained partnerships, community engagement, and replicable research and education models that can be adopted nationally.

Keywords:
CI Contributors and CI Users, Open Source, Quantum Machine Learning (QML), Science and Engineering Research Fields, Curriculum Enhancement, Multi-faceted Training Events

Covered Topics:
The covered topics include:

  • Quantum Support Vector Machine
  • Quantum Neural Network

Prerequisites for Participants:
Basic Python programming skill.