arXiv subjects

Jason Wu

Publications and source records attributed to Jason Wu.

At least 37 records · Page 2Linked to original sources

arXiv2025

The entries of the Sinkhorn limit of an $m \times n$ matrix

We use a variety of computational tools to obtain a degree-$\binom{m + n - 2}{m - 1}$ polynomial equation conjecturally satisfied by the top-left entry of the Sinkhorn limit of a positive $m \times n$ matrix. The degree of this equation has a combinatorial interpretation as the number of minors of an $(m - 1) \times (n - 1)$ matrix, and the coefficients involve a determinant formula that reflects new combinatorial structure on sets of minor specifications. The tools we use include Gröbner bases, which produce equations for small matrices; the PSLQ algorithm, which produces equations for larger matrices as part of an interpolation effort that required 1.5 years of CPU time; and ChatGPT o3-mini-high, which identified the signs of the off-diagonal entries in the determinant formula.

math.NT↗

arXiv2025

MMBind: Unleashing the Potential of Distributed and Heterogeneous Data for Multimodal Learning in IoT

Multimodal sensing systems are increasingly prevalent in various real-world applications. Most existing multimodal learning approaches heavily rely on training with a large amount of synchronized, complete multimodal data. However, such a setting is impractical in real-world IoT sensing applications where data is typically collected by distributed nodes with heterogeneous data modalities, and is also rarely labeled. In this paper, we propose MMBind, a new data binding approach for multimodal learning on distributed and heterogeneous IoT data. The key idea of MMBind is to construct a pseudo-paired multimodal dataset for model training by binding data from disparate sources and incomplete modalities through a sufficiently descriptive shared modality. We also propose a weighted contrastive learning approach to handle domain shifts among disparate data, coupled with an adaptive multimodal learning architecture capable of training models with heterogeneous modality combinations. Evaluations on ten real-world multimodal datasets highlight that MMBind outperforms state-of-the-art baselines under varying degrees of data incompleteness and domain shift, and holds promise for advancing multimodal foundation model training in IoT applications\footnote (The source code is available via https://github.com/nesl/multimodal-bind).

cs.LG↗

arXiv2025

CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development

A persistent challenge in accessible computing is ensuring developers produce web UI code that supports assistive technologies. Despite numerous specialized accessibility tools, novice developers often remain unaware of them, leading to ~96% of web pages that contain accessibility violations. AI coding assistants, such as GitHub Copilot, could offer potential by generating accessibility-compliant code, but their impact remains uncertain. Our formative study with 16 developers without accessibility training revealed three key issues in AI-assisted coding: failure to prompt AI for accessibility, omitting crucial manual steps like replacing placeholder attributes, and the inability to verify compliance. To address these issues, we developed CodeA11y, a GitHub Copilot Extension, that suggests accessibility-compliant code and displays manual validation reminders. We evaluated it through a controlled study with another 20 novice developers. Our findings demonstrate its effectiveness in guiding novice developers by reinforcing accessibility practices throughout interactions, representing a significant step towards integrating accessibility into AI coding assistants.

cs.HC↗

arXiv2024

DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation

Enabling machines to understand structured visuals like slides and user interfaces is essential for making them accessible to people with disabilities. However, achieving such understanding computationally has required manual data collection and annotation, which is time-consuming and labor-intensive. To overcome this challenge, we present a method to generate synthetic, structured visuals with target labels using code generation. Our method allows people to create datasets with built-in labels and train models with a small number of human-annotated examples. We demonstrate performance improvements in three tasks for understanding slides and UIs: recognizing visual elements, describing visual content, and classifying visual content types.

cs.CV↗

arXiv2024

MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases

The deployment of Large Language Models (LLMs) and Large Multimodal Models (LMMs) on mobile devices has gained significant attention due to the benefits of enhanced privacy, stability, and personalization. However, the hardware constraints of mobile devices necessitate the use of models with fewer parameters and model compression techniques like quantization. Currently, there is limited understanding of quantization's impact on various task performances, including LLM tasks, LMM tasks, and, critically, trust and safety. There is a lack of adequate tools for systematically testing these models on mobile devices. To address these gaps, we introduce MobileAIBench, a comprehensive benchmarking framework for evaluating mobile-optimized LLMs and LMMs. MobileAIBench assesses models across different sizes, quantization levels, and tasks, measuring latency and resource consumption on real devices. Our two-part open-source framework includes a library for running evaluations on desktops and an iOS app for on-device latency and hardware utilization measurements. Our thorough analysis aims to accelerate mobile AI research and deployment by providing insights into the performance and feasibility of deploying LLMs and LMMs on mobile platforms.

cs.CL↗

arXiv2024

UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback

Large language models (LLMs) struggle to consistently generate UI code that compiles and produces visually relevant designs. Existing approaches to improve generation rely on expensive human feedback or distilling a proprietary model. In this paper, we explore the use of automated feedback (compilers and multi-modal models) to guide LLMs to generate high-quality UI code. Our method starts with an existing LLM and iteratively produces improved models by self-generating a large synthetic dataset using an original model, applying automated tools to aggressively filter, score, and de-duplicate the data into a refined higher quality dataset. The original LLM is improved by finetuning on this refined dataset. We applied our approach to several open-source LLMs and compared the resulting performance to baseline models with both automated metrics and human preferences. Our evaluation shows the resulting models outperform all other downloadable baselines and approach the performance of larger proprietary models.

cs.CL↗

arXiv2024

FlexLoc: Conditional Neural Networks for Zero-Shot Sensor Perspective Invariance in Object Localization with Distributed Multimodal Sensors

Localization is a critical technology for various applications ranging from navigation and surveillance to assisted living. Localization systems typically fuse information from sensors viewing the scene from different perspectives to estimate the target location while also employing multiple modalities for enhanced robustness and accuracy. Recently, such systems have employed end-to-end deep neural models trained on large datasets due to their superior performance and ability to handle data from diverse sensor modalities. However, such neural models are often trained on data collected from a particular set of sensor poses (i.e., locations and orientations). During real-world deployments, slight deviations from these sensor poses can result in extreme inaccuracies. To address this challenge, we introduce FlexLoc, which employs conditional neural networks to inject node perspective information to adapt the localization pipeline. Specifically, a small subset of model weights are derived from node poses at run time, enabling accurate generalization to unseen perspectives with minimal additional overhead. Our evaluations on a multimodal, multiview indoor tracking dataset showcase that FlexLoc improves the localization accuracy by almost 50% in the zero-shot case (no calibration data available) compared to the baselines. The source code of FlexLoc is available at https://github.com/nesl/FlexLoc.

cs.CV↗

arXiv2024

Efficacy of ByT5 in Multilingual Translation of Biblical Texts for Underrepresented Languages

This study presents the development and evaluation of a ByT5-based multilingual translation model tailored for translating the Bible into underrepresented languages. Utilizing the comprehensive Johns Hopkins University Bible Corpus, we trained the model to capture the intricate nuances of character-based and morphologically rich languages. Our results, measured by the BLEU score and supplemented with sample translations, suggest the model can improve accessibility to sacred texts. It effectively handles the distinctive biblical lexicon and structure, thus bridging the linguistic divide. The study also discusses the model's limitations and suggests pathways for future enhancements, focusing on expanding access to sacred literature across linguistic boundaries.

cs.CL↗

arXiv2024

UIClip: A Data-driven Model for Assessing User Interface Design

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.

cs.HC↗

arXiv2024

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System

The booming success of LLMs initiates rapid development in LLM agents. Though the foundation of an LLM agent is the generative model, it is critical to devise the optimal reasoning strategies and agent architectures. Accordingly, LLM agent research advances from the simple chain-of-thought prompting to more complex ReAct and Reflection reasoning strategy; agent architecture also evolves from single agent generation to multi-agent conversation, as well as multi-LLM multi-agent group chat. However, with the existing intricate frameworks and libraries, creating and evaluating new reasoning strategies and agent architectures has become a complex challenge, which hinders research investigation into LLM agents. Thus, we open-source a new AI agent library, AgentLite, which simplifies this process by offering a lightweight, user-friendly platform for innovating LLM agent reasoning, architectures, and applications with ease. AgentLite is a task-oriented framework designed to enhance the ability of agents to break down tasks and facilitate the development of multi-agent systems. Furthermore, we introduce multiple practical applications developed with AgentLite to demonstrate its convenience and flexibility. Get started now at: \url{https://github.com/SalesforceAIResearch/AgentLite}.

cs.MA↗

arXiv2024

GDTM: An Indoor Geospatial Tracking Dataset with Distributed Multimodal Sensors

Constantly locating moving objects, i.e., geospatial tracking, is essential for autonomous building infrastructure. Accurate and robust geospatial tracking often leverages multimodal sensor fusion algorithms, which require large datasets with time-aligned, synchronized data from various sensor types. However, such datasets are not readily available. Hence, we propose GDTM, a nine-hour dataset for multimodal object tracking with distributed multimodal sensors and reconfigurable sensor node placements. Our dataset enables the exploration of several research problems, such as optimizing architectures for processing multimodal data, and investigating models' robustness to adverse sensing conditions and sensor placement variances. A GitHub repository containing the code, sample data, and checkpoints of this work is available at https://github.com/nesl/GDTM.

cs.RO↗

arXiv2023

Towards Automated Accessibility Report Generation for Mobile Apps

Many apps have basic accessibility issues, like missing labels or low contrast. Automated tools can help app developers catch basic issues, but can be laborious or require writing dedicated tests. We propose a system, motivated by a collaborative process with accessibility stakeholders at a large technology company, 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 qualitative evaluation with 18 accessibility-focused engineers and testers which showed this system can enhance their existing accessibility testing toolkit and address key limitations in current accessibility scanning tools.

cs.HC↗

arXiv2023

Never-ending Learning of User Interfaces

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 that are collected and labeled by human crowd-workers, a process that is costly and surprisingly error-prone for certain tasks. For example, it is possible to guess if a UI element is "tappable" from a screenshot (i.e., based on visual signifiers) or from potentially unreliable metadata (e.g., a view hierarchy), but one way to know for certain is to programmatically tap the UI element and observe the effects. We built the Never-ending UI Learner, an app crawler that automatically installs real apps from a mobile app store and crawls them to discover new and challenging training examples to learn from. The Never-ending UI Learner 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.

cs.HC↗

arXiv2023

Double-lens Scintillometry: The variable scintillation of pulsar B1508+55

We report on observations of PSR B1508+55's scintillation at the Effelsberg 100-m telescope spanning from early 2020 to early 2022. In the autumn of 2020, close to the time the pulsar was predicted to cross echoes in its pulse profile, a sudden transition in the scintillation arcs from peculiar stripe-like features to parabolic arclets was observed. To infer a geometric model of the scattering we measure the effects of the annual velocity curve of Earth, of the relative movement of the line of sight, and of the projection of points on a second scattering screen and develop novel methods to do so. The latter phenomenon was discovered by this study and strongly indicates a two-screen scattering geometry. We derive an analytical two-screen model and demonstrate in a Markov Chain Monte Carlo analysis as well as simulations that it can be successfully applied to explain the observations by interpreting the transition as a change of relative amplitudes of images as well as a shift in the orientation of anisotropy. The collection of methods we demonstrate here is transferable to other pulsars with the potential to strongly improve constraints on scattering models.

astro-ph.HE↗

arXiv2023

WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics

Modeling user interfaces (UIs) from visual information allows systems to make inferences about the functionality and semantics needed to support use cases in accessibility, app automation, and testing. Current datasets for training machine learning models are limited in size due to the costly and time-consuming process of manually collecting and annotating UIs. We crawled the web to construct WebUI, a large dataset of 400,000 rendered web pages associated with automatically extracted metadata. We analyze the composition of WebUI and show that while automatically extracted data is noisy, most examples meet basic criteria for visual UI modeling. We applied several strategies for incorporating semantics found in web pages to increase the performance of visual UI understanding models in the mobile domain, where less labeled data is available: (i) element detection, (ii) screen classification and (iii) screen similarity.

cs.HC↗

arXiv2023

Screen Correspondence: Mapping Interchangeable Elements between UIs

Understanding user interface (UI) functionality is a useful yet challenging task for both machines and people. In this paper, we investigate a machine learning approach for screen correspondence, which allows reasoning about UIs by mapping their elements onto previously encountered examples with known functionality and properties. We describe and implement a model that incorporates element semantics, appearance, and text to support correspondence computation without requiring any labeled examples. Through a comprehensive performance evaluation, we show that our approach improves upon baselines by incorporating multi-modal properties of UIs. Finally, we show three example applications where screen correspondence facilitates better UI understanding for humans and machines: (i) instructional overlay generation, (ii) semantic UI element search, and (iii) automated interface testing.

cs.HC↗

arXiv2022

Reflow: Automatically Improving Touch Interactions in Mobile Applications through Pixel-based Refinements

Touch is the primary way that users interact with smartphones. However, building mobile user interfaces where touch interactions work well for all users is a difficult problem, because users have different abilities and preferences. We propose a system, Reflow, which automatically applies small, personalized UI adaptations, called refinements -- to mobile app screens to improve touch efficiency. Reflow uses a pixel-based strategy to work with existing applications, and improves touch efficiency while minimally disrupting the design intent of the original application. Our system optimizes a UI by (i) extracting its layout from its screenshot, (ii) refining its layout, and (iii) re-rendering the UI to reflect these modifications. We conducted a user study with 10 participants and a heuristic evaluation with 6 experts and found that applications optimized by Reflow led to, on average, 9% faster selection time with minimal layout disruption. The results demonstrate that Reflow's refinements useful UI adaptations to improve touch interactions.

cs.HC↗

arXiv2022

Extracting Replayable Interactions from Videos of Mobile App Usage

Screen recordings of mobile apps are a popular and readily available way for users to share how they interact with apps, such as in online tutorial videos, user reviews, or as attachments in bug reports. Unfortunately, both people and systems can find it difficult to reproduce touch-driven interactions from video pixel data alone. In this paper, we introduce an approach to extract and replay user interactions in videos of mobile apps, using only pixel information in video frames. To identify interactions, we apply heuristic-based image processing and convolutional deep learning to segment screen recordings, classify the interaction in each segment, and locate the interaction point. To replay interactions on another device, we match elements on app screens using UI element detection. We evaluate the feasibility of our pixel-based approach using two datasets: the Rico mobile app dataset and a new dataset of 64 apps with both iOS and Android versions. We find that our end-to-end approach can successfully replay a majority of interactions (iOS--84.1%, Android--78.4%) on different devices, which is a step towards supporting a variety of scenarios, including automatically annotating interactions in existing videos, automated UI testing, and creating interactive app tutorials.

cs.HC↗