There is a growing interest in device-control systems that can interpret human natural language instructions and execute them on a digital device by directly controlling its user interface. We present a dataset for device-control research, Android in the Wild (AitW), which is orders of magnitude larger than current datasets. The dataset contains human demonstrations of device interactions, including the screens and actions, and corresponding natural language instructions. It consists of 715k episodes spanning 30k unique instructions, four versions of Android (v10-13), and eight device types (Pixel 2 XL to Pixel 6) with varying screen resolutions. It contains multi-step tasks that require semantic understanding of language and visual context. This dataset poses a new challenge: actions available through the user interface must be inferred from their visual appearance, and, instead of simple UI element-based actions, the action space consists of precise gestures (e.g., horizontal scrolls to operate carousel widgets). We organize our dataset to encourage robustness analysis of device-control systems, i.e., how well a system performs in the presence of new task descriptions, new applications, or new platform versions. We develop two agents and report performance across the dataset.

The financial markets, which involve over \$90 trillion market capitals, attract the attention of innumerable profit-seeking investors globally. Recent explosion of reinforcement learning in financial trading (RLFT) research has shown stellar performance on many quantitative trading tasks. However, it is still challenging to deploy reinforcement learning (RL) methods into real-world financial markets due to the highly composite nature of this domain, which entails design choices and interactions between components that collect financial data, conduct feature engineering, build market environments, make investment decisions, evaluate model behaviors and offers user interfaces. Despite the availability of abundant financial data and advanced RL techniques, a remarkable gap still exists between the potential and realized utilization of RL in financial trading. In particular, orchestrating an RLFT project lifecycle poses challenges in engineering (i.e.

Meta wants to make its AI hardware slicker and more fashion-forward. It also needs to make its software more usable. The way to do all that appears to be hiring design maestros away from Apple. Meta has made a big move to hire two prominent designers away from rival tech giant Apple, likely putting them to work on designing Meta's next generation of AI hardware and the software that runs on it. Alan Dye, formerly Apple's vice president of Human Interface Design, will join Meta to head up a new design studio within Meta's Reality Labs.

The increasing deployment of autonomous AI agents on the web is hampered by a fundamental misalignment: agents must infer affordances from human-oriented user interfaces, leading to brittle, inefficient, and insecure interactions. To address this, we introduce VOIX, a web-native framework that enables websites to expose reliable, auditable, and privacy-preserving capabilities for AI agents through simple, declarative HTML elements. VOIX introduces and tags, allowing developers to explicitly define available actions and relevant state, thereby creating a clear, machine-readable contract for agent behavior. This approach shifts control to the website developer while preserving user privacy by disconnecting the conversational interactions from the website. We evaluated the framework's practicality, learnability, and expressiveness in a three-day hackathon study with 16 developers. The results demonstrate that participants, regardless of prior experience, were able to rapidly build diverse and functional agent-enabled web applications. Ultimately, this work provides a foundational mechanism for realizing the Agentic Web, enabling a future of seamless and secure human-AI collaboration on the web.

Effective decision-making often relies on timely insights from complex visual data. While Information Visualization (InfoVis) dashboards can support this process, they rarely adapt to users' cognitive state, and less so in real time. We present Symbiotik, an intelligent, context-aware adaptive visualization system that leverages neurophysiological signals to estimate mental workload (MWL) and dynamically adapt visual dashboards using reinforcement learning (RL). Through a user study with 120 participants and three visualization types, we demonstrate that our approach improves task performance and engagement. Symbiotik offers a scalable, real-time adaptation architecture, and a validated methodology for neuroadaptive user interfaces.

We support different padding strategies and alphabet sizes, but by default we choose an alphabet size of 96, where the last character is used for padding.

The integration of machine learning (ML) is critical for industrial competitiveness, yet its adoption is frequently stalled by the prohibitive costs and operational disruptions of upgrading legacy systems. The financial and logistical overhead required to support the full ML lifecycle presents a formidable barrier to widespread implementation, particularly for small and medium-sized enterprises. This paper introduces a pragmatic, API-based framework designed to overcome these challenges by strategically decoupling the ML model lifecycle from the production environment. Our solution delivers the analytical power of ML to domain experts through a lightweight, browser-based interface, eliminating the need for local hardware upgrades and ensuring model maintenance can occur with zero production downtime. This human-in-the-loop approach empowers experts with interactive control over model parameters, fostering trust and facilitating seamless integration into existing workflows. By mitigating the primary financial and operational risks, this framework offers a scalable and accessible pathway to enhance production quality and safety, thereby strengthening the competitive advantage of the manufacturing sector.

Knowledge tracing (KT) models are a crucial basis for pedagogical decision-making, namely which task to select next for a learner and when to stop teaching a particular skill. Given the high stakes of pedagogical decisions, KT models are typically required to be interpretable, in the sense that they should implement an explicit model of human learning and provide explicit estimates of learners' abilities. However, to our knowledge, no study to date has investigated whether the interpretability of KT models actually helps human teachers to make teaching decisions. We address this gap. First, we perform a simulation study to show that, indeed, decisions based on interpretable KT models achieve mastery faster compared to decisions based on a non-interpretable model. Second, we repeat the study but ask $N=12$ human teachers to make the teaching decisions based on the information provided by KT models. As expected, teachers rate interpretable KT models higher in terms of usability and trustworthiness. However, the number of tasks needed until mastery hardly differs between KT models. This suggests that the relationship between model interpretability and teacher decisions is not straightforward: teachers do not solely rely on KT models to make decisions and further research is needed to investigate how learners and teachers actually understand and use KT models.

Large language models (LLMs) are increasingly seen as assistants, copilots, and consultants, capable of supporting a wide range of tasks through natural conversation. However, most systems remain constrained by a linear request-response format that often makes interactions inefficient in multi-turn, information-dense, and exploratory tasks. To address these limitations, we propose Generative Interfaces for Language Models, a paradigm in which LLMs respond to user queries by proactively generating user interfaces (UIs) that enable more adaptive and interactive engagement. Our framework leverages structured interface-specific representations and iterative refinements to translate user queries into task-specific UIs. For systematic evaluation, we introduce a multidimensional assessment framework that compares generative interfaces with traditional chat-based ones across diverse tasks, interaction patterns, and query types, capturing functional, interactive, and emotional aspects of user experience. Results show that generative interfaces consistently outperform conversational ones, with up to a 72% improvement in human preference. These findings clarify when and why users favor generative interfaces, paving the way for future advancements in human-AI interaction.