Text-to-image (T2I) generation has made significant advances in recent years, but challenges still remain in the generation of perceptual artifacts, misalignment with complex prompts, and safety. The prevailing approach to address these issues involves collecting human feedback on generated images, training reward models to estimate human feedback, and then fine-tuning T2I models based on the reward models to align them with human preferences. However, while existing reward fine-tuning methods can produce images with higher rewards, they may change model behavior in unexpected ways. For example, fine-tuning for one quality aspect (e.g., safety) may degrade other aspects (e.g., prompt alignment), or may lead to reward hacking (e.g., finding a way to increase rewards without having the intended effect). In this paper, we propose Focus-N-Fix, the first region-aware fine-tuning method that trains models to correct only previously problematic image regions. The resulting fine-tuned model generates images with the same high-level structure as the original model but shows significant improvements in regions where the original model was deficient in safety (over-sexualization and violence), plausibility, or other criteria. Our experiments demonstrate that Focus-N-Fix improves these localized quality aspects with little or no degradation to others and typically imperceptible changes in the rest of the image. Disclaimer: This paper contains images that may be overly sexual, violent, offensive or harmful.

Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively established. This paper investigates the effectiveness of fine-grained feedback which captures nuanced distinctions in image quality and prompt-alignment, compared to traditional coarse-grained feedback (for example, thumbs up/down or ranking between a set of options). While fine-grained feedback holds promise, particularly for systems catering to diverse societal preferences, we show that demonstrating its superiority to coarse-grained feedback is not automatic. Through experiments on real and synthetic preference data, we surface the complexities of building effective models due to the interplay of model choice, feedback type, and the alignment between human judgment and computational interpretation. We identify key challenges in eliciting and utilizing fine-grained feedback, prompting a reassessment of its assumed benefits and practicality. Our findings -- e.g., that fine-grained feedback can lead to worse models for a fixed budget, in some settings; however, in controlled settings with known attributes, fine grained rewards can indeed be more helpful -- call for careful consideration of feedback attributes and potentially beckon novel modeling approaches to appropriately unlock the potential value of fine-grained feedback in-the-wild.

Macros are building block tasks of our everyday smartphone activity (e.g., "login", or "booking a flight"). Effectively extracting macros is important for understanding mobile interaction and enabling task automation. These macros are however difficult to extract at scale as they can be comprised of multiple steps yet hidden within programmatic components of mobile apps. In this paper, we introduce a novel approach based on Large Language Models (LLMs) to automatically extract semantically meaningful macros from both random and user-curated mobile interaction traces. The macros produced by our approach are automatically tagged with natural language descriptions and are fully executable. We conduct multiple studies to validate the quality of extracted macros, including user evaluation, comparative analysis against human-curated tasks, and automatic execution of these macros. These experiments and analyses demonstrate the effectiveness of our approach and the usefulness of extracted macros in various downstream applications.

We explore the boundaries of scaling up a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. Our model advances the state-of-the-art on most vision-and-language benchmarks considered (20+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix.

Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues such as artifacts/implausibility, misalignment with text descriptions, and low aesthetic quality. Inspired by the success of Reinforcement Learning with Human Feedback (RLHF) for large language models, prior works collected human-provided scores as feedback on generated images and trained a reward model to improve the T2I generation. In this paper, we enrich the feedback signal by (i) marking image regions that are implausible or misaligned with the text, and (ii) annotating which words in the text prompt are misrepresented or missing on the image. We collect such rich human feedback on 18K generated images (RichHF-18K) and train a multimodal transformer to predict the rich feedback automatically. We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions. Notably, the improvements generalize to models (Muse) beyond those used to generate the images on which human feedback data were collected (Stable Diffusion variants). The RichHF-18K data set will be released in our GitHub repository: https://github.com/google-research/google-research/tree/master/richhf_18k.

Progress in human behavior modeling involves understanding both implicit, early-stage perceptual behavior, such as human attention, and explicit, later-stage behavior, such as subjective preferences or likes. Yet most prior research has focused on modeling implicit and explicit human behavior in isolation; and often limited to a specific type of visual content. We propose UniAR -- a unified model of human attention and preference behavior across diverse visual content. UniAR leverages a multimodal transformer to predict subjective feedback, such as satisfaction or aesthetic quality, along with the underlying human attention or interaction heatmaps and viewing order. We train UniAR on diverse public datasets spanning natural images, webpages, and graphic designs, and achieve SOTA performance on multiple benchmarks across various image domains and behavior modeling tasks. Potential applications include providing instant feedback on the effectiveness of UIs/visual content, and enabling designers and content-creation models to optimize their creation for human-centric improvements.

Automated UI evaluation can be beneficial for the design process; for example, to compare different UI designs, or conduct automated heuristic evaluation. LLM-based UI evaluation, in particular, holds the promise of generalizability to a wide variety of UI types and evaluation tasks. However, current LLM-based techniques do not yet match the performance of human evaluators. We hypothesize that automatic evaluation can be improved by collecting a targeted UI feedback dataset and then using this dataset to enhance the performance of general-purpose LLMs. We present a targeted dataset of 3,059 design critiques and quality ratings for 983 mobile UIs, collected from seven designers, each with at least a year of professional design experience. We carried out an in-depth analysis to characterize the dataset’s features. We then applied this dataset to achieve a 55% performance gain in LLM-generated UI feedback via various few-shot and visual prompting techniques. We also discuss future applications of this dataset, including training a reward model for generative UI techniques, and fine-tuning a tool-agnostic multi-modal LLM that automates UI evaluation.

Conversational agents show the promise to allow users to interact with mobile devices using language. However, to perform diverse UI tasks with natural language, developers typically need to create separate datasets and models for each specific task, which is expensive and effort-consuming. Recently, pre-trained large language models (LLMs) have been shown capable of generalizing to various downstream tasks when prompted with a handful of examples from the target task. This paper investigates the feasibility of enabling versatile conversational interactions with mobile UIs using a single LLM. We designed prompting techniques to adapt an LLM to mobile UIs. We experimented with four important modeling tasks that address various scenarios in conversational interaction. Our method achieved competitive performance on these challenging tasks without requiring dedicated datasets and training, offering a lightweight and generalizable approach to enable language-based mobile interaction.

Layout design is an important task in various design fields, including user interfaces, document, and graphic design. As this task requires tedious manual effort by designers, prior works have attempted to automate this process using generative models, but commonly fell short of providing intuitive user controls and achieving design objectives. In this paper, we build a conditional latent diffusion model, PLay, that generates parametrically conditioned layouts in vector graphic space from user-specified guidelines, which are commonly used by designers for representing their design intents in current practices. Our method outperforms prior works across three datasets on metrics including FID and FD-VG, and in user test. Moreover, it brings a novel and interactive experience to professional layout design processes.

The layout of a mobile screen is a critical data source for UI design research and semantic understanding of the screen. However, UI layouts in existing datasets are often noisy, have mismatches with their visual representation, or consists of generic or app-specific types that are difficult to analyze and model. In this paper, we propose the CLAY pipeline that uses a deep learning approach for denoising UI layouts, allowing us to automatically improve existing mobile UI layout datasets at scale. Our pipeline takes both the screenshot and the raw UI layout, and annotates the raw layout by removing incorrect nodes and assigning a semantically meaningful type to each node. To experiment with our data-cleaning pipeline, we create the CLAY dataset of 59,555 human-annotated screen layouts, based on screenshots and raw layouts from Rico, a public mobile UI corpus. Our deep models achieve high accuracy with F1 scores of 82.7% for detecting layout objects that do not have a valid visual representation and 85.9% for recognizing object types, which significantly outperforms a heuristic baseline. Our work lays a foundation for creating large-scale high quality UI layout datasets for data-driven mobile UI research and reduces the need of manual labeling efforts that are prohibitively expensive.

UI designers often correct false affordances and improve the discoverability of features when users have trouble determining if elements are tappable. We contribute a novel system that models the perceived tappability of mobile UI elements with a vision-based deep neural network and helps provide design insights with dataset-level and instance-level explanations of model predictions. Our system retrieves designs from similar mobile UI examples from our dataset using the latent space of our model. We also contribute a novel use of an interpretability algorithm, XRAI, to generate a heatmap of UI elements that contribute to a given tappability prediction. Through several examples, we show how our system can help automate elements of UI usability analysis and provide insights for designers to iterate their designs. In addition, we share findings from an exploratory evaluation with professional designers to learn how AI-based tools can aid UI design and evaluation for tappability issues.

User interface design is a complex task that involves designers examining a wide range of options. We present Spacewalker, a tool that allows designers to rapidly search a large design space for an optimal web UI with integrated support. Designers first annotate each attribute they want to explore in a typical HTML page, using a simple markup extension we designed. Spacewalker then parses the annotated HTML specification, and intelligently generates and distributes various configurations of the web UI to crowd workers for evaluation. We enhanced a genetic algorithm to accommodate crowd worker responses from pairwise comparison of UI designs, which is crucial for obtaining reliable feedback. Based on our experiments, Spacewalker allows designers to effectively search a large design space of a UI, using the language they are familiar with, and improve their design rapidly at a minimal cost.

Attentional mechanisms are order-invariant. Positional encoding is a crucial component to allow attention-based deep model architectures such as Transformer to address sequences or images where the position of information matters. In this paper, we propose a novel positional encoding method based on learnable Fourier features. Instead of hard-coding each position as a token or a vector, we represent each position, which can be multi-dimensional, as a trainable encoding based on learnable Fourier feature mapping, modulated with a multi-layer perceptron. The representation is particularly advantageous for a spatial multi-dimensional position, e.g., pixel positions on an image, where $L_2$ distances or more complex positional relationships need to be captured. Our experiments based on several public benchmark tasks show that our learnable Fourier feature representation for multi-dimensional positional encoding outperforms existing methods by both improving the accuracy and allowing faster convergence.

We present HelpViz, a tool for generating contextual visual mobile tutorials from text-based instructions that are abundant on the web. HelpViz transforms text instructions to graphical tutorials in batch, by extracting a sequence of actions from each text instruction through an instruction parsing model, and executing the extracted actions on a simulation infrastructure that manages an array of Android emulators. The automatic execution of each instruction produces a set of graphical and structural assets, including images, videos, and metadata such as clicked elements for each step. HelpViz then synthesizes a tutorial by combining parsed text instructions with the generated assets, and contextualizes the tutorial to user interaction by tracking the user’s progress and highlighting the next step. Our experiments with HelpViz indicate that our pipeline improved tutorial execution robustness and that participants preferred tutorials generated by HelpViz over text-based instructions. HelpViz promises a cost-effective approach for generating contextual visual tutorials for mobile interaction at scale.

Mobile User Interface Summarization generates succinct language descriptions of mobile screens for conveying important contents and functionalities of the screen, which can be useful for many language-based application scenarios. We present Screen2Words, a novel screen summarization approach that automatically encapsulates essential information of a UI screen into a coherent language phrase. Summarizing mobile screens requires a holistic understanding of the multi-modal data of mobile UIs, including text, image, structures as well as UI semantics, motivating our multi-modal learning approach. We collected and analyzed a large-scale screen summarization dataset annotated by human workers. Our dataset contains more than 112k language summarization across ∼ 22k unique UI screens. We then experimented with a set of deep models with different configurations. Our evaluation of these models with both automatic accuracy metrics and human rating shows that our approach can generate high-quality summaries for mobile screens. We demonstrate potential use cases of Screen2Words and open-source our dataset and model to lay the foundations for further bridging language and user interfaces.

Natural language descriptions of user interface (UI) elements such as alternative text are crucial for accessibility and language-based interaction in general.Yet, these descriptions are constantly missing in mobile UIs.We propose widget captioning, a novel task for automatically generating language descriptions for UI elements from multimodal input including both the image and the structural representations of user interfaces.We collected a largescale dataset for widget captioning with crowdsourcing.Our dataset contains 162,859 language phrases created by human workers for annotating 61,285 UI elements across 21,750 unique UI screens.We thoroughly analyze the dataset, and train and evaluate a set of deep model configurations to investigate how each feature modality as well as the choice of learning strategies impact the quality of predicted captions.The task formulation and the dataset as well as our benchmark models contribute a solid basis for this novel multimodal captioning task that connects language and user interfaces.

MicroRNAs (miRNAs) regulate a wide range of cellular and developmental processes through gene expression suppression or mRNA degradation. Experimentally validated miRNA gene targets are often reported in the literature. In this paper, we describe miRTex, a text mining system that extracts miRNA-target relations, as well as miRNA-gene and gene-miRNA regulation relations. The system achieves good precision and recall when evaluated on a literature corpus of 150 abstracts with F-scores close to 0.90 on the three different types of relations. We conducted full-scale text mining using miRTex to process all the Medline abstracts and all the full-length articles in the PubMed Central Open Access Subset. The results for all the Medline abstracts are stored in a database for interactive query and file download via the website at http://proteininformationresource.org/mirtex. Using miRTex, we identified genes potentially regulated by miRNAs in Triple Negative Breast Cancer, as well as miRNA-gene relations that, in conjunction with kinase-substrate relations, regulate the response to abiotic stress in Arabidopsis thaliana. These two use cases demonstrate the usefulness of miRTex text mining in the analysis of miRNA-regulated biological processes.

We introduce RLIMS-P version 2.0, an enhanced rule-based information extraction (IE) system for mining kinase, substrate, and phosphorylation site information from scientific literature. Consisting of natural language processing and IE modules, the system has integrated several new features, including the capability of processing full-text articles and generalizability towards different post-translational modifications (PTMs). To evaluate the system, sets of abstracts and full-text articles, containing a variety of textual expressions, were annotated. On the abstract corpus, the system achieved F-scores of 0.91, 0.92, and 0.95 for kinases, substrates, and sites, respectively. The corresponding scores on the full-text corpus were 0.88, 0.91, and 0.92. It was additionally evaluated on the corpus of the 2013 BioNLP-ST GE task, and achieved an F-score of 0.87 for the phosphorylation core task, improving upon the results previously reported on the corpus. Full-scale processing of all abstracts in MEDLINE and all articles in PubMed Central Open Access Subset has demonstrated scalability for mining rich information in literature, enabling its adoption for biocuration and for knowledge discovery. The new system is generalizable and it will be adapted to tackle other major PTM types. RLIMS-P 2.0 online system is available online (http://proteininformationresource.org/rlimsp/) and the developed corpora are available from iProLINK (http://proteininformationresource.org/iprolink/).