YN
Y. Noviello
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
4 records found
1
ANVIL
Analogies and Videos for Lecturers
We present ANVIL, a multimodal generative system that automates the production of analogy-based instructional animations for computer science topics. Given a concept definition, ANVIL generates a textual analogy, compiles it into a structured visual screenplay, and produces executable manim code to render an animation, with an automated repair mechanism to improve robustness. Evaluating such systems at scale requires balancing pedagogical validity with scalability. We begin with a teacher evaluation to ground the quality assessment and use its findings to guide automated screening. For textual analogies, we introduce an LLM-based evaluator for scalable quality screening; for videos, where subjective judgments are difficult to automate, we instead assess fidelity to the intended screenplay using an automated proxy for auditing and error analysis. We further conduct a user study with educators to examine adoption requirements and risks. Our findings suggest that ANVIL can produce materials that are frequently rated as adequate, and that educators respond positively to its perceived value and usability.
...
We present ANVIL, a multimodal generative system that automates the production of analogy-based instructional animations for computer science topics. Given a concept definition, ANVIL generates a textual analogy, compiles it into a structured visual screenplay, and produces executable manim code to render an animation, with an automated repair mechanism to improve robustness. Evaluating such systems at scale requires balancing pedagogical validity with scalability. We begin with a teacher evaluation to ground the quality assessment and use its findings to guide automated screening. For textual analogies, we introduce an LLM-based evaluator for scalable quality screening; for videos, where subjective judgments are difficult to automate, we instead assess fidelity to the intended screenplay using an automated proxy for auditing and error analysis. We further conduct a user study with educators to examine adoption requirements and risks. Our findings suggest that ANVIL can produce materials that are frequently rated as adequate, and that educators respond positively to its perceived value and usability.
AI-Generated Traces for Novice Programmers
Learning Effects and Learner Differences in a Multi-Institutional Study
Conference paper
(2026)
-
Yuri Noviello, Naaz Sibia, Anastasiia Birillo, Thomas Overklift Vaupel Klein, Michael Liut, Gosia Migut
Introductory programming (CS1) courses often struggle to support students' understanding of program execution. While visualizations can make execution processes explicit, their effectiveness depends on design and context, and empirical evidence for AI-generated visualizations remains limited. We propose Generated Animated Traces (GATs), AI-generated, analogy-based, narrated animations that coordinate source code, execution state, and conceptual analogies. We conduct a study at two institutions in CS1 courses (Python N=961; Java N=151) comparing GATs to textual explanations. We measure immediate learning performance and experience, end-of-course engagement and exam performance. Results show that GATs can yield selective benefits for immediate learning, but benefits are context-dependent and short-term. We observe that GATs' influence on performance is moderated by learner engagement profiles. This finding underscores the importance of personalized approaches.
...
Introductory programming (CS1) courses often struggle to support students' understanding of program execution. While visualizations can make execution processes explicit, their effectiveness depends on design and context, and empirical evidence for AI-generated visualizations remains limited. We propose Generated Animated Traces (GATs), AI-generated, analogy-based, narrated animations that coordinate source code, execution state, and conceptual analogies. We conduct a study at two institutions in CS1 courses (Python N=961; Java N=151) comparing GATs to textual explanations. We measure immediate learning performance and experience, end-of-course engagement and exam performance. Results show that GATs can yield selective benefits for immediate learning, but benefits are context-dependent and short-term. We observe that GATs' influence on performance is moderated by learner engagement profiles. This finding underscores the importance of personalized approaches.
Effectively teaching programming concepts remains a persistent challenge, as conventional approaches often struggle to make abstract ideas accessible and engaging. Analogies provide a powerful means to simplify these concepts, and when augmented with multimodal resources, such as video animations, can significantly enhance learner engagement and comprehension. This research leverages Large Language Models (LLMs) and a structured animation workflow to automate the generation of analogy-driven explanations and visualizations for programming topics. Preliminary findings indicate that while LLMs can produce creative and pedagogically relevant analogies, careful decomposition and validation steps are critical for ensuring clarity, correctness, and learning alignment. We will conduct controlled evaluations to compare the effectiveness of AI-generated analogy-driven materials against traditional instructional methods. We also explore domain-specific personalization, adapting analogies to the learner’s familiar domains and background.
...
Effectively teaching programming concepts remains a persistent challenge, as conventional approaches often struggle to make abstract ideas accessible and engaging. Analogies provide a powerful means to simplify these concepts, and when augmented with multimodal resources, such as video animations, can significantly enhance learner engagement and comprehension. This research leverages Large Language Models (LLMs) and a structured animation workflow to automate the generation of analogy-driven explanations and visualizations for programming topics. Preliminary findings indicate that while LLMs can produce creative and pedagogically relevant analogies, careful decomposition and validation steps are critical for ensuring clarity, correctness, and learning alignment. We will conduct controlled evaluations to compare the effectiveness of AI-generated analogy-driven materials against traditional instructional methods. We also explore domain-specific personalization, adapting analogies to the learner’s familiar domains and background.
Engaging students with effective learning materials continues to be a significant challenge in programming education. Analogies are commonly used to simplify complex topics, enabling learners to relate unfamiliar concepts to familiar ones. Additionally, visual representations of these analogies can enhance engagement and improve the overall learning experience. This work presents a prototype of a novel AI tool that generates analogy-based explanations and corresponding video animations for programming education. The tool leverages Large Language Models (LLMs) for analogy generation and a structured animation workflow for visualization. This poster invites discussion on the effectiveness of AI-generated educational content and its implications for programming education.
...
Engaging students with effective learning materials continues to be a significant challenge in programming education. Analogies are commonly used to simplify complex topics, enabling learners to relate unfamiliar concepts to familiar ones. Additionally, visual representations of these analogies can enhance engagement and improve the overall learning experience. This work presents a prototype of a novel AI tool that generates analogy-based explanations and corresponding video animations for programming education. The tool leverages Large Language Models (LLMs) for analogy generation and a structured animation workflow for visualization. This poster invites discussion on the effectiveness of AI-generated educational content and its implications for programming education.