In this paper, we present several results of both theoretical as well as practical interests. First, we propose the quota lawn mowing problem, an extension of the classic lawn mowing problem in computational geometry, as follows: given a quota of coverage, compute the shortest lawn mowing route to achieve said quota. We give constant-factor approximations for the quota lawn mowing problem. Second, we investigate the expected detection time minimization problem in geometric coverage path planning with local, continuous sensory information. We provide the first approximation algorithm with provable error bounds with pseudopolynomial running time. Our ideas also extend to another search mechanism, namely visibility-based search, which is related to the watchman route problem. We complement our theoretical analysis with some simple but effective heuristics for finding an object in minimum expected time, on which we provide simulation results.

In the evolving landscape of AI regulation, it is crucial for companies to conduct impact assessments and document their compliance through comprehensive reports. However, current reports lack grounding in regulations and often focus on specific aspects like privacy in relation to AI systems, without addressing the real-world uses of these systems. Moreover, there is no systematic effort to design and evaluate these reports with both AI practitioners and AI compliance experts. To address this gap, we conducted an iterative co-design process with 14 AI practitioners and 6 AI compliance experts and proposed a template for impact assessment reports grounded in the EU AI Act, NIST's AI Risk Management Framework, and ISO 42001 AI Management System. We evaluated the template by producing an impact assessment report for an AI-based meeting companion at a major tech company. A user study with 8 AI practitioners from the same company and 5 AI compliance experts from industry and academia revealed that our template effectively provides necessary information for impact assessments and documents the broad impacts of AI systems. Participants envisioned using the template not only at the pre-deployment stage for compliance but also as a tool to guide the design stage of AI uses.

The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. In this paper, we focus on machine translation (MT), a task that has been shown to benefit from in-context translation examples. However no systematic studies have been published on how best to select examples, and mixed results have been reported on the usefulness of similarity-based selection over random selection. We provide a study covering multiple LLMs and multiple in-context example retrieval strategies, comparing multilingual sentence embeddings. We cover several language directions, representing different levels of language resourcedness (English into French, German, Swahili and Wolof). Contrarily to previously published results, we find that sentence embedding similarity can improve MT, especially for low-resource language directions, and discuss the balance between selection pool diversity and quality. We also highlight potential problems with the evaluation of LLM-based MT and suggest a more appropriate evaluation protocol, adapting the COMET metric to the evaluation of LLMs. Code and outputs are freely available at https://github.com/ArmelRandy/ICL-MT.

Recent developments in wearable devices have made accurate and efficient seizure detection more important than ever. A challenge in seizure detection is that patient-specific models typically outperform patient-independent models. However, in a wearable device one typically starts with a patient-independent model, until such patient-specific data is available. To avoid having to construct a new classifier with this data, as required in conventional kernel machines, we propose a transfer learning approach with a tensor kernel machine. This method learns the primal weights in a compressed form using the canonical polyadic decomposition, making it possible to efficiently update the weights of the patient-independent model with patient-specific data. The results show that this patient fine-tuned model reaches as high a performance as a patient-specific SVM model with a model size that is twice as small as the patient-specific model and ten times as small as the patient-independent model.

The head of the Sudanese Armed Forces, General Abdel Fattah al-Burhan survived a drone strike on the Gebeit army base while attending a graduation ceremony. Five people were killed in the strike.

Sudan's army leader, General Abdel Fattah al-Burhan, says the military will not join talks next month in Switzerland aimed at ending more than a year of fighting with the paramilitary Rapid Support Forces (RSF). Al-Burhan made the statement on Wednesday, shortly after the military said he survived a drone strike on a military graduation at the Gibeit army base in eastern Sudan that killed at least five people. "We will not retreat, we will not surrender and we will not negotiate," al-Burhan told troops. "We are not scared of drones," he said at the Gibeit base, which is about 100km (62 miles) southwest of Port Sudan, where the army-aligned government fled after war broke out with the RSF in April last year. The fighting has created the world's largest displacement crisis and killed at least 15,500 people, according to United Nations estimates. Video of the drone attack, verified by the Reuters news agency, showed soldiers marching in a graduation ceremony before a whirring sound can be heard.

Previous talks to end the conflict, which has created the world's largest humanitarian crisis, have failed as both sides have refused to honour their commitments. More than 10 million people have fled their homes since the former allies fell out over an internationally backed political plan to move towards civilian rule. The Jabait army base is about 100km (62 miles) from Port Sudan, the military's de facto capital and where Gen Burhan is based. Video footage being shared from those attending the ceremony on Wednesday morning shows military graduates marching in ceremonial dress before the sound of a strike. "The only party that is hostile to the Sudanese people and targeting the Sudanese people is the rebel Rapid Support Forces," Gen Abdallah told the BBC.

This issue usually stems from the assumption that crowdworkers are a homogeneous group [56], neglecting their diverse cultural backgrounds [90]. Moreover, a notable trend in design has emerged advocating for minimizing cultural impact in work interfaces, aiming for global uniformity in their design rather than customizing these systems to accommodate cultural nuances [133, 134, 193]. Consequently, many work interfaces have strived for uniform standards, and have ignored worker diversity [76, 84, 88]. However, interfaces often reflect the cultural biases of their designers [18], inadvertently embedding their cultural norms [146, 150, 177]. This can lead to designs that unintentionally require "outside workers" to adapt or modify their behaviors [126, 177], potentially hindering their success and effectiveness in their jobs [24, 60, 64, 85]. A solution can be to create culturally aware tools for crowdworkers, yet research into integrating culture theory into such designs remains limited [108, 118, 163]. Further research is crucial to assess these systems' effectiveness and their potential benefits for crowdworkers from varied cultural backgrounds. To address this knowledge gap, we focus on designing a tool that aims to enhance crowdworkers' experiences by incorporating cultural considerations.

Machine learning (ML) on tabular data is ubiquitous, yet obtaining abundant high-quality tabular data for model training remains a significant obstacle. Numerous works have focused on tabular data augmentation (TDA) to enhance the original table with additional data, thereby improving downstream ML tasks. Recently, there has been a growing interest in leveraging the capabilities of generative AI for TDA. Therefore, we believe it is time to provide a comprehensive review of the progress and future prospects of TDA, with a particular emphasis on the trending generative AI. Specifically, we present an architectural view of the TDA pipeline, comprising three main procedures: pre-augmentation, augmentation, and post-augmentation. Pre-augmentation encompasses preparation tasks that facilitate subsequent TDA, including error handling, table annotation, table simplification, table representation, table indexing, table navigation, schema matching, and entity matching. Augmentation systematically analyzes current TDA methods, categorized into retrieval-based methods, which retrieve external data, and generation-based methods, which generate synthetic data. We further subdivide these methods based on the granularity of the augmentation process at the row, column, cell, and table levels. Post-augmentation focuses on the datasets, evaluation and optimization aspects of TDA. We also summarize current trends and future directions for TDA, highlighting promising opportunities in the era of generative AI. In addition, the accompanying papers and related resources are continuously updated and maintained in the GitHub repository at https://github.com/SuDIS-ZJU/awesome-tabular-data-augmentation to reflect ongoing advancements in the field.

Detecting out-of-distribution (OOD) samples is crucial for ensuring the safety of machine learning systems and has shaped the field of OOD detection. Meanwhile, several other problems are closely related to OOD detection, including anomaly detection (AD), novelty detection (ND), open set recognition (OSR), and outlier detection (OD). To unify these problems, a generalized OOD detection framework was proposed, taxonomically categorizing these five problems. However, Vision Language Models (VLMs) such as CLIP have significantly changed the paradigm and blurred the boundaries between these fields, again confusing researchers. In this survey, we first present a generalized OOD detection v2, encapsulating the evolution of AD, ND, OSR, OOD detection, and OD in the VLM era. Our framework reveals that, with some field inactivity and integration, the demanding challenges have become OOD detection and AD. In addition, we also highlight the significant shift in the definition, problem settings, and benchmarks; we thus feature a comprehensive review of the methodology for OOD detection, including the discussion over other related tasks to clarify their relationship to OOD detection. Finally, we explore the advancements in the emerging Large Vision Language Model (LVLM) era, such as GPT-4V. We conclude this survey with open challenges and future directions.