arXiv subjects

Pedro Alejandro Perez

Publications and source records attributed to Pedro Alejandro Perez.

3 recordsLinked to original sources

arXiv2025

DynEx: Dynamic Code Synthesis with Structured Design Exploration for Accelerated Exploratory Programming

Recent advancements in large language models have significantly expedited the process of generating front-end code. This allows users to rapidly prototype user interfaces and ideate through code, a process known as exploratory programming. However, existing LLM code generation tools focus more on technical implementation details rather than finding the right design given a particular problem. We present DynEx, an LLM-based method for design exploration in accelerated exploratory programming. DynEx introduces a technique to explore the design space through a structured Design Matrix before creating the prototype with a modular, stepwise approach to LLM code generation. Code is generated sequentially, and users can test and approve each step before moving onto the next. A user study of 10 experts found that DynEx increased design exploration and enabled the creation of more complex and varied prototypes compared to a Claude Artifact baseline. We conclude with a discussion of the implications of design exploration for exploratory programming.

cs.HC↗

arXiv2024

DIDUP: Dynamic Iterative Development for UI Prototyping

Large language models (LLMs) are remarkably good at writing code. A particularly valuable case of human-LLM collaboration is code-based UI prototyping, a method for creating interactive prototypes that allows users to view and fully engage with a user interface. We conduct a formative study of GPT Pilot, a leading LLM-generated code-prototyping system, and find that its inflexibility towards change once development has started leads to weaknesses in failure prevention and dynamic planning; it closely resembles the linear workflow of the waterfall model. We introduce DIDUP, a system for code-based UI prototyping that follows an iterative spiral model, which takes changes and iterations that come up during the development process into account. We propose three novel mechanisms for LLM-generated code-prototyping systems: (1) adaptive planning, where plans should be dynamic and reflect changes during implementation, (2) code injection, where the system should write a minimal amount of code and inject it instead of rewriting code so users have a better mental model of the code evolution, and (3) lightweight state management, a simplified version of source control so users can quickly revert to different working states. Together, this enables users to rapidly develop and iterate on prototypes.

cs.HC↗

arXiv2024

Scrolly2Reel: Retargeting Graphics for Social Media Using Narrative Beats

Content retargeting is crucial for social media creators. Once great content is created, it is important to reach as broad an audience as possible. This is particularly important in journalism where younger audiences are shifting away from print and towards short-video platforms. Many newspapers already create rich graphics for the web that they want to be able to reuse for social media. One example is scrollytelling sequences or "scrollies" -- immersive articles with graphics like animation, charts, and 3D visualizations that appear as a user scrolls. We present a system that helps transform scrollies into social media videos. By using the scriptwriting concept of narrative beats to extract fundamental storytelling units, we can create videos that are more aligned with narration, and allow for better pacing and stylistic changes. Narrative beats are thus an important primitive to retargeting content that matches the style of a new medium while maintaining the cohesiveness of the original content.

cs.HC↗