S2.2 Varianceofimportanceweights The importance-sampled estimate of the log-likelihood used to retrain the oracle (Equation 17) is unbiased, butmayhavehighvariance duetothevariance oftheimportance weights. LetLβ: X R Rdenote a pertinent loss function induced by the oracle parameters,β, (e.g., the squared errorLβ(x,y) = (Eβ[y |x] y)2). While the bound,L, on Lβ may be restrictive in general, for any givenapplication one may beable touse domain-specific knowledge toestimateL. CbAS naturally controls the importance weight variance. Design procedures that leverage a trust region can naturally bound thevariance oftheimportance weights.

Inspired by biological evolution, we explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derive that both of them have consistent mathematical representation. Analogous to the dynamic local population in EA, we improve the existing transformer structure and propose a more efficient EAT model, and design task-related heads to deal with different tasks more flexibly. Moreover, we introduce the spatial-filling curve into the current vision transformer to sequence image data into a uniform sequential format. Thus we can design a unified EAT framework to address multi-modal tasks, separating the network architecture from the data format adaptation. Our approach achieves state-of-the-art results on the ImageNet classification task compared with recent vision transformer works while having smaller parameters and greater throughput. We further conduct multi-modal tasks to demonstrate the superiority of the unified EAT, \eg, Text-Based Image Retrieval, and our approach improves the rank-1 by +3.7 points over the baseline on the CSS dataset.

Online optimization covers problems such as online resource allocation, online bipartite matching, adwords (a central problem in e-commerce and advertising), and adwords with separable concave returns. We analyze the worst case competitive ratio of two primal-dual algorithms for a class of online convex (conic) optimization problems that contains the previous examples as special cases defined on the positive orthant. We derive a sufficient condition on the objective function that guarantees a constant worst case competitive ratio (greater than or equal to $\frac{1}{2}$) for monotone objective functions. We provide new examples of online problems on the positive orthant % and the positive semidefinite cone that satisfy the sufficient condition. We show how smoothing can improve the competitive ratio of these algorithms, and in particular for separable functions, we show that the optimal smoothing can be derived by solving a convex optimization problem. This result allows us to directly optimize the competitive ratio bound over a class of smoothing functions, and hence design effective smoothing customized for a given cost function.

The high-dimensional convolution is widely used in various disciplines but has a serious performance problem due to its high computational complexity. Over the decades, people took a handmade approach to design fast algorithms for the Gaussian convolution. Recently, requirements for various non-Gaussian convolutions have emerged and are continuously getting higher. However, the handmade acceleration approach is no longer feasible for so many different convolutions since it is a time-consuming and painstaking job. Instead, we propose an Acceleration Network (AccNet) which turns the work of designing new fast algorithms to training the AccNet. This is done by: 1, interpreting splatting, blurring, slicing operations as convolutions; 2, turning these convolutions to $g$CP layers to build AccNet. After training, the activation function $g$ together with AccNet weights automatically define the new splatting, blurring and slicing operations. Experiments demonstrate AccNet is able to design acceleration algorithms for a ton of convolutions including Gaussian/non-Gaussian convolutions and produce state-of-the-art results.

Limited English proficiency (LEP) patients in the U.S. face systemic barriers to healthcare beyond language and interpreter access, encompassing procedural and institutional constraints. AI advances may support communication and care through on-demand translation and visit preparation, but also risk exacerbating existing inequalities. We conducted storyboard-driven interviews with 14 patient navigators to explore how AI could shape care experiences for Spanish-speaking LEP individuals. We identified tensions around linguistic and cultural misunderstandings, privacy concerns, and opportunities and risks for AI to augment care workflows. Participants highlighted structural factors that can undermine trust in AI systems, including sensitive information disclosure, unstable technology access, and low digital literacy. While AI tools can potentially alleviate social barriers and institutional constraints, there are risks of misinformation and uprooting human camaraderie. Our findings contribute design considerations for AI that support LEP patients and care teams via rapport-building, education, and language support, and minimizing disruptions to existing practices.

As Artificial Intelligence (AI) increasingly impacts professional practice, there is a growing need to AI-related competencies into higher education curricula. However, research on the implementation of AI education within study programs remains limited and requires new forms of collaboration across disciplines. This study addresses this gap and explores perspectives on interdisciplinary curriculum development through the lens of different stakeholders. In particular, we examine the case of curriculum development for a novel undergraduate program in AI in engineering. The research uses a mixed methods approach, combining quantitative curriculum mapping with qualitative focus group interviews. In addition to assessing the alignment of the curriculum with the targeted competencies, the study also examines the perceived quality, consistency, practicality and effectiveness from both academic and industry perspectives, as well as differences in perceptions between educators who were involved in the development and those who were not. The findings provide a practical understanding of the outcomes of interdisciplinary AI curriculum development and contribute to a broader understanding of how educator participation in curriculum development influences perceptions of quality aspects. It also advances the field of AI education by providing a reference point and insights for further interdisciplinary curriculum developments in response to evolving industry needs.

Welcome to your essential guide to functional safety, tailored specifically for product developers. In a world where technology is increasingly integrated into every aspect of our lives—from industrial robots to autonomous vehicles—the potential for harm from product malfunctions makes functional safety not just important, but critical. This webinar cuts through the complexity to provide a clear understanding of what functional safety truly entails and why it's critical for product success. We'll start by defining functional safety not by its often-confusing official terms, but as a structured methodology for managing risk through defined engineering processes, essential product design requirements, and probabilistic analysis. The “north star” goals? To ensure your product not only works reliably but, if it does fail, it does so in a safe and predictable manner. We'll dive into two fundamental concepts: the Safety Lifecycle, a detailed engineering process focused on design quality to minimize systematic failures, and Probabilistic, Performance-Based Design using reliability metrics to minimize random hardware failures. You'll learn about IEC 61508, the foundational standard for functional safety, and how numerous industry-specific standards derive from it. The webinar will walk you through the Engineering Design phases: analyzing hazards and required risk reduction, realizing optimal designs, and ensuring safe operation. We'll demystify the Performance Concept and the critical Safety Integrity Level (SIL), explaining its definition, criteria (systematic capability, architectural constraints, PFD), and how it relates to industry-specific priorities. Discover key Design Verification techniques like DFMEA/DDMA and FMEDA, emphasizing how these tools help identify and address problems early in development. We'll detail the FMEDA technique showing how design decisions directly impact predictions like safe and dangerous failure rates, diagnostic coverage, and useful life. Finally, we'll cover Functional Safety Certification, explaining its purpose, process, and what adjustments to your development process can set you up for success.

Topological Data Analysis (TDA) has emerged as a powerful framework for extracting robust and interpretable features from noisy high-dimensional data. In the context of Social Choice Theory, where preference profiles and collective decisions are geometrically rich yet sensitive to perturbations, TDA remains largely unexplored. This work introduces a novel conceptual bridge between these domains by proposing a new metric framework for persistence diagrams tailored to noisy preference data.We define a polar coordinate-based distance that captures both the magnitude and orientation of topological features in a smooth and differentiable manner. Our metric addresses key limitations of classical distances, such as bottleneck and Wasserstein, including instability under perturbation, lack of continuity, and incompatibility with gradient-based learning. The resulting formulation offers improved behavior in both theoretical and applied settings.To the best of our knowledge, this is the first study to systematically apply persistent homology to social choice systems, providing a mathematically grounded method for comparing topological summaries of voting structures and preference dynamics. We demonstrate the superiority of our approach through extensive experiments, including robustness tests and supervised learning tasks, and we propose a modular pipeline for building predictive models from online preference data. This work contributes a conceptually novel and computationally effective tool to the emerging interface of topology and decision theory, opening new directions in interpretable machine learning for political and economic systems.

Recent advances in large language models (LLMs) offer unprecedented opportunities to enhance human-AI collaboration in qualitative research methods, including interviews. While interviews are highly valued for gathering deep, contextualized insights, interviewers often face significant cognitive challenges, such as real-time information processing, question adaptation, and rapport maintenance. My doctoral research introduces Interview AI-ssistant, a system designed for real-time interviewer-AI collaboration during both the preparation and execution phases. Through four interconnected studies, this research investigates the design of effective human-AI collaboration in interviewing contexts, beginning with a formative study of interviewers' needs, followed by a prototype development study focused on AI-assisted interview preparation, an experimental evaluation of real-time AI assistance during interviews, and a field study deploying the system in a real-world research setting. Beyond informing practical implementations of intelligent interview support systems, this work contributes to the Intelligent User Interfaces (IUI) community by advancing the understanding of human-AI collaborative interfaces in complex social tasks and establishing design guidelines for AI-enhanced qualitative research tools.

AI-assisted learning companion robots are increasingly used in early education. Many parents express concerns about content appropriateness, while they also value how AI and robots could supplement their limited skill, time, and energy to support their children's learning. We designed a card-based kit, SET, to systematically capture scenarios that have different extents of parental involvement. We developed a prototype interface, PAiREd, with a learning companion robot to deliver LLM-generated educational content that can be reviewed and revised by parents. Parents can flexibly adjust their involvement in the activity by determining what they want the robot to help with. We conducted an in-home field study involving 20 families with children aged 3-5. Our work contributes to an empirical understanding of the level of support parents with different expectations may need from AI and robots and a prototype that demonstrates an innovative interaction paradigm for flexibly including parents in supporting their children.