Despite being trained on vast amounts of data, most LLMs are unable to reliably generate well-designed UIs. Designer feedback is essential to improving performance on UI generation; however, we find that existing RLHF methods based on ratings or rankings are not well-aligned with with designers' workflows and ignore the rich rationale used to critique and improve UI designs. In this paper, we investigate several approaches for designers to give feedback to UI generation models, using familiar interactions such as commenting, sketching and direct manipulation. We first perform an evaluation with 21 designers where they gave feedback using these interactions, which resulted in 1500 design annotations. We then use this data to finetune a series of LLMs to generate higher quality UIs. Finally, we evaluate these models with human judges, and we find that our designer-aligned approaches outperform models trained with traditional ranking feedback and all tested baselines, including GPT-5.

UI prototyping often involves iterating and blending elements from examples such as screenshots and sketches, but current tools offer limited support for incorporating these examples.Inspired by the cognitive process of conceptual blending, we introduce a novel UI workflow that allows developers to rapidly incorporate diverse aspects from design examples into work-in-progress UIs.We prototyped this workflow as Misty.Through a exploratory first-use study with 14 frontend developers, we assessed Misty's effectiveness and gathered feedback on this workflow.Our findings suggest

Publisher Copyright: © 2025 Copyright held by the owner/author(s).

Developers and quality assurance testers often rely on manual testing to test accessibility features throughout the product lifecycle. Unfortunately, manual testing can be tedious, often has an overwhelming scope, and can be difficult to schedule amongst other development milestones. Recently, Large Language Models (LLMs) have been used for a variety of tasks including automation of UIs. However, to our knowledge, no one has yet explored the use of LLMs in controlling assistive technologies for the purposes of supporting accessibility testing. In this paper, we explore the requirements of a natural language based accessibility testing workflow, starting with a formative study. From this we build a system that takes a manual accessibility test instruction in natural language (e.g., “Search for a show in VoiceOver”) as input and uses an LLM combined with pixel-based UI Understanding models to execute the test and produce a chaptered, navigable video. In each video, to help QA testers, we apply heuristics to detect and flag accessibility issues (e.g., Text size not increasing with Large Text enabled, VoiceOver navigation loops). We evaluate this system through a 10-participant user study with accessibility QA professionals who indicated that the tool would be very useful in their current work and performed tests similarly to how they would manually test the features. The study also reveals insights for future work on using LLMs for accessibility testing.

User interface (UI) design is a difficult yet important task for ensuring the usability, accessibility, and aesthetic qualities of applications. In our paper, we develop a machine-learned model, UIClip, for assessing the design quality and visual relevance of a UI given its screenshot and natural language description. To train UIClip, we used a combination of automated crawling, synthetic augmentation, and human ratings to construct a large-scale dataset of UIs, collated by description and ranked by design quality. Through training on the dataset, UIClip implicitly learns properties of good and bad designs by i) assigning a numerical score that represents a UI design’s relevance and quality and ii) providing design suggestions. In an evaluation that compared the outputs of UIClip and other baselines to UIs rated by 12 human designers, we found that UIClip achieved the highest agreement with ground-truth rankings. Finally, we present three example applications that demonstrate how UIClip can facilitate downstream applications that rely on instantaneous assessment of UI design quality: i) UI code generation, ii) UI design tips generation, and iii) quality-aware UI example search.

Many apps have basic accessibility issues, like missing labels or low contrast. To supplement manual testing, automated tools can help developers and QA testers find basic accessibility issues, but they can be laborious to use or require writing dedicated tests. To motivate our work, we interviewed eight accessibility QA professionals at a large technology company. From these interviews, we synthesized three design goals for accessibility report generation systems. Motivated by these goals, we developed a system to generate whole app accessibility reports by combining varied data collection methods (e.g., app crawling, manual recording) with an existing accessibility scanner. Many such scanners are based on single-screen scanning, and a key problem in whole app accessibility reporting is to effectively de-duplicate and summarize issues collected across an app. To this end, we developed a screen grouping model with 96.9% accuracy (88.8% F1-score) and UI element matching heuristics with 97% accuracy (98.2% F1-score). We combine these technologies in a system to report and summarize unique issues across an app, and enable a unique pixel-based ignore feature to help engineers and testers better manage reported issues across their app’s lifetime. We conducted a user study where 19 accessibility engineers and testers used multiple tools to create lists of prioritized issues in the context of an accessibility audit. Our system helped them create lists they were more satisfied with while addressing key limitations of current accessibility scanning tools.

Machine learning models have been trained to predict semantic information about user interfaces (UIs) to make apps more accessible, easier to test, and to automate. Currently, most models rely on datasets of static screenshots that are labeled by human annotators, a process that is costly and surprisingly error-prone for certain tasks. For example, workers labeling whether a UI element is “tappable” from a screenshot must guess using visual signifiers, and do not have the benefit of tapping on the UI element in the running app and observing the effects. In this paper, we present the Never-ending UI Learner, an app crawler that automatically installs real apps from a mobile app store and crawls them to infer semantic properties of UIs by interacting with UI elements, discovering new and challenging training examples to learn from, and continually updating machine learning models designed to predict these semantics. The Never-ending UI Learner so far has crawled for more than 5,000 device-hours, performing over half a million actions on 6,000 apps to train three computer vision models for i) tappability prediction, ii) draggability prediction, and iii) screen similarity.

Accurately recognizing icon types in mobile applications is integral to many tasks, including accessibility improvement, UI design search, and conversational agents. Existing research focuses on recognizing the most frequent icon types, but these technologies fail when encountering an unrecognized low-frequency icon. In this paper, we work towards complete coverage of icons in the wild. After annotating a large-scale icon dataset (327,879 icons) from iPhone apps, we found a highly uneven distribution: 98 common icon types covered 92.8% of icons, while 7.2% of icons were covered by more than 331 long-tail icon types. In order to label icons with widely varying occurrences in apps, our system uses an image classification model to recognize common icon types with an average of 3,000 examples each (96.3% accuracy) and applies a few-shot learning model to classify long-tail icon types with an average of 67 examples each (78.6% accuracy). Our system also detects contextual information that helps characterize icon semantics, including nearby text (95.3% accuracy) and modifier symbols added to the icon (87.4% accuracy). In a validation study with workers (n = 23), we verified the usefulness of our generated icon labels. The icon types supported by our work cover 99.5% of collected icons, improving on the previously highest 78% coverage in icon classification work.

All graphical user interfaces are comprised of one or more screens that may be shown to the user depending on their interactions. Identifying different screens of an app and understanding the type of changes that happen on the screens is a challenging task that can be applied in many areas including automatic app crawling, playback of app automation macros and large scale app dataset analysis. For example, an automated app crawler needs to understand if the screen it is currently viewing is the same as any previous screen that it has encountered, so it can focus its efforts on portions of the app that it has not yet explored. Moreover, identifying the type of change on the screen, such as whether any dialogues or keyboards have opened or closed, is useful for an automatic crawler to handle such events while crawling. Understanding screen relationships is a difficult task as instances of the same screen may have visual and structural variation, for example due to different content in a database-backed application, scrolling, dialog boxes opening or closing, or content loading delays. At the same time, instances of different screens from the same app may share some similarities in terms of design, structure, and content. This paper uses a dataset of screenshots from more than 1K iPhone applications to train two ML models that understand similarity in different ways: (1) a screen similarity model that combines a UI object detector with a transformer model architecture to recognize instances of the same screen from a collection of screenshots from a single app, and (2) a screen transition model that uses a siamese network architecture to identify both similarity and three types of events that appear in an interaction trace: the keyboard or a dialog box appearing or disappearing, and scrolling. Our models achieve an F1 score of 0.83 on the screen similarity task, improving on comparable baselines, and an average F1 score of 0.71 across all events in the transition task.

People often capture photos or notes from their phones to integrate later into a document. But current mobile capture tools can make this hard, with the captured information ending up fragmented and decontextualized. This paper explores how to help document authors capture, contextualize, and use document-related information. A survey of 66 information workers reveals that document-focused information capture differs from other types of mobile information capture, and that while people capture a broad range of information types while mobile, most document-related capture comes in the form of photos, notes, and bookmarks. Based on this survey we built Scraps, which consists of two parts: 1) a mobile app that makes it easy for people to capture and add context to information from their phone, and 2) a Word sidebar that helps them later link that information to a document on their desktop. In a field study with 11 information workers, we find that Scraps streamlined the process of capturing and using document-related information, and enabled people to focus on writing over integrating captured information.

Many accessibility features available on mobile platforms require applications (apps) to provide complete and accurate metadata describing user interface (UI) components. Unfortunately, many apps do not provide sufficient metadata for accessibility features to work as expected. In this paper, we explore inferring accessibility metadata for mobile apps from their pixels, as the visual interfaces often best reflect an app’s full functionality. We trained a robust, fast, memory-efficient, on-device model to detect UI elements using a dataset of 77,637 screens (from 4,068 iPhone apps) that we collected and annotated. To further improve UI detections and add semantic information, we introduced heuristics (e.g., UI grouping and ordering) and additional models (e.g., recognize UI content, state, interactivity). We built Screen Recognition to generate accessibility metadata to augment iOS VoiceOver. In a study with 9 screen reader users, we validated that our approach improves the accessibility of existing mobile apps, enabling even previously inaccessible apps to be used.

Although exploring alternatives is fundamental to creating better interface designs, current processes for creating alternatives are generally manual, limiting the alternatives a designer can explore. We present Scout, a system that helps designers rapidly explore alternatives through mixed-initiative interaction with high-level constraints and design feedback. Prior constraint-based layout systems use low-level spatial constraints and generally produce a single design. Tosupport designer exploration of alternatives, Scout introduces high-level constraints based on design concepts (e.g.,~semantic structure, emphasis, order) and formalizes them into low-level spatial constraints that a solver uses to generate potential layouts. In an evaluation with 18 interface designers, we found that Scout: (1) helps designers create more spatially diverse layouts with similar quality to those created with a baseline tool and (2) can help designers avoid a linear design process and quickly ideate layouts they do not believe they would have thought of on their own.

Tapping is an immensely important gesture in mobile touchscreen interfaces, yet people still frequently are required to learn which elements are tappable through trial and error. Predicting human behavior for this everyday gesture can help mobile app designers understand an important aspect of the usability of their apps without having to run a user study. In this paper, we present an approach for modeling tappability of mobile interfaces at scale. We conducted large-scale data collection of interface tappability over a rich set of mobile apps using crowdsourcing and computationally investigated a variety of signifiers that people use to distinguish tappable versus not-tappable elements. Based on the dataset, we developed and trained a deep neural network that predicts how likely a user will perceive an interface element as tappable versus not tappable. Using the trained tappability model, we developed TapShoe, a tool that automatically diagnoses mismatches between the tappability of each element as perceived by a human user---predicted by our model, and the intended or actual tappable state of the element specified by the developer or designer. Our model achieved reasonable accuracy: mean precision 90.2% and recall 87.0%, in matching human perception on identifying tappable UI elements. The tappability model and TapShoe were well received by designers via an informal evaluation with 7 professional interaction designers.

Interface designers often use screenshot images of example designs as building blocks for new designs. Since images are unstructured and hard to edit, designers typically reconstruct screenshots with vector graphics tools in order to reuse or edit parts of the design. Unfortunately, this reconstruction process is tedious and slow. We present Rewire, an interactive system that helps designers leverage example screenshots. Rewire automatically infers a vector representation of screenshots where each UI component is a separate object with editable shape and style properties. Based on this representation, the system provides three design assistance modes that help designers reuse or redraw components of the example design. The results from our quantitative and user evaluations demonstrate that Rewire can generate accurate vector representations of interface screenshots found in the wild and that design assistance enables users to reconstruct and edit example designs more efficiently compared to a baseline design tool.

Most web applications are designed as one-size-fits-all, despite considerable variation in people's expertise, physical abilities, and other factors that impact interaction. For example, some web applications require the use of a mouse, precluding use by many people with severe motor disabilities. Other applications require laborious manual input that a skilled developer could automate if the application were scriptable. This paper presents Genie, a system that automatically reverse engineers an abstract model of the underlying commands in a web application, then enables interaction with that functionality through alternative interfaces and other input modalities (e.g., speech, keyboard, or command line input). Genie comprises an abstract model of command properties, behaviors, and dependencies as well as algorithms that reverse engineer this model from an existing web application through static and dynamic program analysis. We evaluate Genie by developing several interfaces that automatically add support for speech, keyboard, and command line input to arbitrary web applications.

As software systems evolve, new interface features such as keyboard shortcuts and toolbars are introduced. While it is common to regression test the new features for functional correctness, there has been less focus on systematic regression testing for usability, due to the effort and time involved in human studies. Cognitive modeling tools such as CogTool provide some help by computing predictions of user performance, but they still require manual effort to describe the user interface and tasks, limiting regression testing efforts. In recent work, we developed CogTool-Helper to reduce the effort required to generate human performance models of existing systems. We build on this work by providing task specific test case generation and present our vision for human performance regression testing (HPRT) that generates large numbers of test cases and evaluates a range of human performance predictions for the same task. We examine the feasibility of HPRT on four tasks in LibreOffice, find several regressions, and then discuss how a project team could use this information. We also illustrate that we can increase efficiency with sampling by leveraging an inference algorithm. Samples that take approximately 50% of the runtime lose at most 10% of the performance predictions.

With the rise of tools for predictive human performance modeling in HCI comes a need to model legacy applications. Models of legacy systems are used to compare products to competitors, or new proposed design ideas to the existing version of an application. We present CogTool-Helper, an exemplar of a tool that results from joining this HCI need to research in automatic GUI testing from the Software Engineering testing community. CogTool-Helper uses automatic UI-model extraction and test case generation to automatically create CogTool storyboards and models and infer methods to accomplish tasks beyond what the UI designer has specified. A design walkthrough with experienced CogTool users reveal that CogTool-Helper resonates with a "pain point" of real-world modeling and provide suggestions for future work.