Jason Wu

Taejun Kim, Amy Karlson, Aakar Gupta et al.

While text entry is an essential and frequent task in Augmented Reality (AR) applications, devising an efficient and easy-to-use text entry method for AR remains an open challenge. This research presents STAR, a smartphone-analogous AR text entry technique that leverages a user's familiarity with smartphone two-thumb typing. With STAR, a user performs thumb typing on a virtual QWERTY keyboard that is overlain on the skin of their hands. During an evaluation study of STAR, participants achieved a mean typing speed of 21.9 WPM (i.e., 56% of their smartphone typing speed), and a mean error rate of 0.3% after 30 minutes of practice. We further analyze the major factors implicated in the performance gap between STAR and smartphone typing, and discuss ways this gap could be narrowed.

Yi-Hao Peng, Faria Huq, Yue Jiang et al.

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.

Zhiwei Liu, Weiran Yao, Jianguo Zhang et al. · salesforce

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}.

Jason Wu, Eldon Schoop, Alan Leung et al.

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.

Jason Wu, Ziqi Wang, Xiaomin Ouyang et al.

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.

Jason Wu, Tianchen Zhao, Chang Liu et al.

Large Vision-Language Models (LVLMs) use their vision encoders to translate images into representations for downstream reasoning, but the encoders often underperform in domain-specific visual tasks such as medical image diagnosis or fine-grained classification, where representation errors can cascade through the language model, leading to incorrect responses. Existing adaptation methods modify the continuous feature interface between encoder and language model through projector tuning or other parameter-efficient updates, which still couples the two components and requires re-alignment whenever the encoder changes. We introduce CRAFT (Codebook RegulAted Fine-Tuning), a lightweight method that fine-tunes the encoder using a discrete codebook that anchors visual representations to a stable token space, achieving domain adaptation without modifying other parts of the model. This decoupled design allows the adapted encoder to seamlessly boost the performance of LVLMs with different language architectures, as long as they share the same codebook. Empirically, CRAFT achieves an average gain of 13.51% across 10 domain-specific benchmarks such as VQARAD and PlantVillage, while preserving the LLM's linguistic capabilities and outperforming peer methods that operate on continuous tokens.

Jason Wu, Yi-Hao Peng, Amanda Li et al.

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.

Yi-Hao Peng, Jeffrey P. Bigham, Jason Wu

Generative models, such as large language models and text-to-image diffusion models, are increasingly used to create visual designs like user interfaces (UIs) and presentation slides. Finetuning and benchmarking these generative models have often relied on datasets of human-annotated design preferences. Yet, due to the subjective and highly personalized nature of visual design, preference varies widely among individuals. In this paper, we study this problem by introducing DesignPref, a dataset of 12k pairwise comparisons of UI design generation annotated by 20 professional designers with multi-level preference ratings. We found that among trained designers, substantial levels of disagreement exist (Krippendorff's alpha = 0.25 for binary preferences). Natural language rationales provided by these designers indicate that disagreements stem from differing perceptions of various design aspect importance and individual preferences. With DesignPref, we demonstrate that traditional majority-voting methods for training aggregated judge models often do not accurately reflect individual preferences. To address this challenge, we investigate multiple personalization strategies, particularly fine-tuning or incorporating designer-specific annotations into RAG pipelines. Our results show that personalized models consistently outperform aggregated baseline models in predicting individual designers' preferences, even when using 20 times fewer examples. Our work provides the first dataset to study personalized visual design evaluation and support future research into modeling individual design taste.

Jason Wu, Amanda Swearngin, Arun Krishna Vajjala et al.

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 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 a study 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.

Paul Pu Liang, Yiwei Lyu, Xiang Fan et al.

Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. It is a challenging yet crucial area with numerous real-world applications in multimedia, affective computing, robotics, finance, human-computer interaction, and healthcare. Unfortunately, multimodal research has seen limited resources to study (1) generalization across domains and modalities, (2) complexity during training and inference, and (3) robustness to noisy and missing modalities. In order to accelerate progress towards understudied modalities and tasks while ensuring real-world robustness, we release MultiBench, a systematic and unified large-scale benchmark spanning 15 datasets, 10 modalities, 20 prediction tasks, and 6 research areas. MultiBench provides an automated end-to-end machine learning pipeline that simplifies and standardizes data loading, experimental setup, and model evaluation. To enable holistic evaluation, MultiBench offers a comprehensive methodology to assess (1) generalization, (2) time and space complexity, and (3) modality robustness. MultiBench introduces impactful challenges for future research, including scalability to large-scale multimodal datasets and robustness to realistic imperfections. To accompany this benchmark, we also provide a standardized implementation of 20 core approaches in multimodal learning. Simply applying methods proposed in different research areas can improve the state-of-the-art performance on 9/15 datasets. Therefore, MultiBench presents a milestone in unifying disjoint efforts in multimodal research and paves the way towards a better understanding of the capabilities and limitations of multimodal models, all the while ensuring ease of use, accessibility, and reproducibility. MultiBench, our standardized code, and leaderboards are publicly available, will be regularly updated, and welcomes inputs from the community.

Jason Wu, Gabriel Reyes, Sam C. White et al.

Numerous accessibility features have been developed and included in consumer operating systems to provide people with a variety of disabilities additional ways to access computing devices. Unfortunately, many users, especially older adults who are more likely to experience ability changes, are not aware of these features or do not know which combination to use. In this paper, we first quantify this problem via a survey with 100 participants, demonstrating that very few people are aware of built-in accessibility features on their phones. These observations led us to investigate accessibility recommendation as a way to increase awareness and adoption. We developed four prototype recommenders that span different accessibility categories, which we used to collect insights from 20 older adults. Our work demonstrates the need to increase awareness of existing accessibility features on mobile devices, and shows that automated recommendation could help people find beneficial accessibility features.

Xiaoyi Zhang, Lilian de Greef, Amanda Swearngin et al.

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.

Jaylin Herskovitz, Jason Wu, Samuel White et al.

Augmented Reality (AR) technology creates new immersive experiences in entertainment, games, education, retail, and social media. AR content is often primarily visual and it is challenging to enable access to it non-visually due to the mix of virtual and real-world content. In this paper, we identify common constituent tasks in AR by analyzing existing mobile AR applications for iOS, and characterize the design space of tasks that require accessible alternatives. For each of the major task categories, we create prototype accessible alternatives that we evaluate in a study with 10 blind participants to explore their perceptions of accessible AR. Our study demonstrates that these prototypes make AR possible to use for blind users and reveals a number of insights to move forward. We believe our work sets forth not only exemplars for developers to create accessible AR applications, but also a roadmap for future research to make AR comprehensively accessible.

Sean Wang, Yuxiao Hu, Jason Wu

The demand for smartness in embedded systems has been mounting up drastically in the past few years. Embedded system today must address the fundamental challenges introduced by cloud computing and artificial intelligence. KubeEdge [1] is an edge computing framework build on top of Kubernetes [2]. It provides compute resource management, deployment, runtime and operation capabilities on geo-located edge computing resources, from the cloud, which is a natural fit for embedded systems. Here we propose KubeEdge.AI, an edge AI framework on top of KubeEdge. It provides a set of key modules and interfaces: a data handling and processing engine, a concise AI runtime, a decision engine, and a distributed data query interface. KubeEdge.AI will help reduce the burdens for developing specific edge/embedded AI systems and promote edge-cloud coordination and synergy.