Radio remains a pervasive medium for mass information dissemination, with AM/FM stations reaching more Americans than either smartphone-based social networking or live television. Increasingly, radio broadcasts are also streamed online and accessed over the Internet. We present WavePulse, a framework that records, documents, and analyzes radio content in real-time. While our framework is generally applicable, we showcase the efficacy of WavePulse in a collaborative project with a team of political scientists focusing on the 2024 Presidential Elections. We use WavePulse to monitor livestreams of 396 news radio stations over a period of three months, processing close to 500,000 hours of audio streams. These streams were converted into time-stamped, diarized transcripts and analyzed to track answer key political science questions at both the national and state levels. Our analysis revealed how local issues interacted with national trends, providing insights into information flow. Our results demonstrate WavePulse's efficacy in capturing and analyzing content from radio livestreams sourced from the Web. Code and dataset can be accessed at \url{https://wave-pulse.io}.

'"Close-up person in '"Street" all are smoking" Methods like Dreambooth lead to substantial drift in previously learned representations during the finetuning process even when adapting to as few as five images: a) Appearance drift: Columns demonstrate fine-grained class changes, complete object and scene shifts, and alterations in color (on both rows, images are generated from same seed). Recent advances in diffusion models have significantly enhanced image generation capabilities. However, customizing these models with new classes often leads to unintended consequences that compromise their reliability. We introduce the concept of open-world forgetting to emphasize the vast scope of these unintended alterations, contrasting it with the well-studied closed-world forgetting, which is measurable by evaluating performance on a limited set of classes or skills. Our research presents the first comprehensive investigation into open-world forgetting in diffusion models, focusing on semantic and appearance drift of representations. We utilize zero-shot classification to analyze semantic drift, revealing that even minor model adaptations lead to unpredictable shifts affecting areas far beyond newly introduced concepts, with dramatic drops in zero-shot classification of up to 60%. Additionally, we observe significant changes in texture and color of generated content when analyzing appearance drift. To address these issues, we propose a mitigation strategy based on functional regularization, designed to preserve original capabilities while accommodating new concepts. Our study aims to raise awareness of unintended changes due to model customization and advocates for the analysis of open-world forgetting in future research on model customization and finetuning methods. Furthermore, we provide insights for developing more robust adaptation methodologies. Recent advancements in image generation have led to the development of remarkably powerful foundational models capable of synthesizing highly realistic and diverse visual content. Techniques such as Generative Adversarial Networks (GANs) (Goodfellow et al., 2014), and more recently autoregressive models (Yu et al., 2022), Rectified Flows (Liu et al., 2023), and Denoising Diffusion Probabilistic Models (DDPMs) (Ho et al., 2020), have each contributed to significant progress in the field. These methods offer unique strengths in sample quality, diversity, and controllability. Among them, diffusion models have gained particular prominence due to their recent successes and growing influence, especially in enabling text-based image generation (Shonenkov et al., 2023; Ramesh et al., 2022) and complementary multimodal conditioning (Zhang & Agrawala, 2023; Mou et al., 2023), making them a key focus in current research and applications.

Large language models (LLMs) are trained on a vast amount of human-written data, but data providers often remain uncredited. In response to this issue, data valuation (or data attribution), which quantifies the contribution or value of each data to the model output, has been discussed as a potential solution. Nevertheless, applying existing data valuation methods to recent LLMs and their vast training datasets has been largely limited by prohibitive compute and memory costs. In this work, we focus on influence functions, a popular gradient-based data valuation method, and significantly improve its scalability with an efficient gradient projection strategy called LoGra that leverages the gradient structure in backpropagation. We then provide a theoretical motivation of gradient projection approaches to influence functions to promote trust in the data valuation process. Lastly, we lower the barrier to implementing data valuation systems by introducing LogIX, a software package that can transform existing training code into data valuation code with minimal effort. In our data valuation experiments, LoGra achieves competitive accuracy against more expensive baselines while showing up to 6,500x improvement in throughput and 5x reduction in GPU memory usage when applied to Llama3-8B-Instruct and the 1B-token dataset.

Despite advancements in on-topic dialogue systems, effectively managing topic shifts within dialogues remains a persistent challenge, largely attributed to the limited availability of training datasets. To address this issue, we propose Multi-Passage to Dialogue (MP2D), a data generation framework that automatically creates conversational question-answering datasets with natural topic transitions. By leveraging the relationships between entities in a knowledge graph, MP2D maps the flow of topics within a dialogue, effectively mirroring the dynamics of human conversation. It retrieves relevant passages corresponding to the topics and transforms them into dialogues through the passage-to-dialogue method. Through quantitative and qualitative experiments, we demonstrate MP2D's efficacy in generating dialogue with natural topic shifts. Furthermore, this study introduces a novel benchmark for topic shift dialogues, TS-WikiDialog. Utilizing the dataset, we demonstrate that even Large Language Models (LLMs) struggle to handle topic shifts in dialogue effectively, and we showcase the performance improvements of models trained on datasets generated by MP2D across diverse topic shift dialogue tasks.

Many important computer vision applications are naturally formulated as regression problems. Within medical imaging, accurate regression models have the potential to automate various tasks, helping to lower costs and improve patient outcomes. Such safety-critical deployment does however require reliable estimation of model uncertainty, also under the wide variety of distribution shifts that might be encountered in practice. Motivated by this, we set out to investigate the reliability of regression uncertainty estimation methods under various real-world distribution shifts. To that end, we propose an extensive benchmark of 8 image-based regression datasets with different types of challenging distribution shifts. We then employ our benchmark to evaluate many of the most common uncertainty estimation methods, as well as two state-of-the-art uncertainty scores from the task of out-of-distribution detection. We find that while methods are well calibrated when there is no distribution shift, they all become highly overconfident on many of the benchmark datasets. This uncovers important limitations of current uncertainty estimation methods, and the proposed benchmark therefore serves as a challenge to the research community. We hope that our benchmark will spur more work on how to develop truly reliable regression uncertainty estimation methods. Code is available at https://github.com/fregu856/regression_uncertainty.

Latest advances in Super-Resolution (SR) have been tested with general purpose images such as faces, landscapes and objects, mainly unused for the task of super-resolving Earth Observation (EO) images. In this research paper, we benchmark state-of-the-art SR algorithms for distinct EO datasets using both Full-Reference and No-Reference Image Quality Assessment (IQA) metrics. We also propose a novel Quality Metric Regression Network (QMRNet) that is able to predict quality (as a No-Reference metric) by training on any property of the image (i.e. its resolution, its distortions...) and also able to optimize SR algorithms for a specific metric objective. This work is part of the implementation of the framework IQUAFLOW which has been developed for evaluating image quality, detection and classification of objects as well as image compression in EO use cases. We integrated our experimentation and tested our QMRNet algorithm on predicting features like blur, sharpness, snr, rer and ground sampling distance (GSD) and obtain validation medRs below 1.0 (out of N=50) and recall rates above 95\%. Overall benchmark shows promising results for LIIF, CAR and MSRN and also the potential use of QMRNet as Loss for optimizing SR predictions. Due to its simplicity, QMRNet could also be used for other use cases and image domains, as its architecture and data processing is fully scalable.

The increasing number of product reviews posted online is a gold mine for designers to know better about the products they develop, by capturing the voice of customers, and to improve these products accordingly. In the meantime, product design and development have an essential role in creating a more sustainable future. With the recent advance of artificial intelligence techniques in the field of natural language processing, this research aims to develop an integrated machine learning solution to obtain sustainable design insights from online product reviews automatically. In this paper, the opportunities and challenges offered by existing frameworks - including Python libraries, packages, as well as state-of-the-art algorithms like BERT - are discussed, illustrated, and positioned along an ad hoc machine learning process. This contribution discusses the opportunities to reach and the challenges to address for building a machine learning pipeline, in order to get insights from product reviews to design more sustainable products, including the five following stages, from the identification of sustainability-related reviews to the interpretation of sustainable design leads: data collection, data formatting, model training, model evaluation, and model deployment. Examples of sustainable design insights that can be produced out of product review mining and processing are given. Finally, promising lines for future research in the field are provided, including case studies putting in parallel standard products with their sustainable alternatives, to compare the features valued by customers and to generate in fine relevant sustainable design leads.

The aircraft carrier Nimitz is finally going home. The Pentagon last month ordered the warship to remain in the Middle East because of Iranian threats against President Donald J. Trump and other American officials, just three days after announcing the ship was returning home as a signal to de-escalate rising tensions with Tehran. With those immediate tensions seeming to ease a bit, and President Biden looking to renew discussions with Iran on the 2015 nuclear accord that Mr. Trump withdrew from, three Defense Department officials said on Monday that the Nimitz and its 5,000-member crew were ordered on Sunday to return to the ship's home port of Bremerton, Wash., after a longer-than-usual 10-month deployment. The Pentagon for weeks had been engaged in a muscle-flexing strategy aimed at deterring Iran and its Shia proxies in Iraq from attacking American personnel in the Persian Gulf to avenge the death of Maj. General Suleimani, the commander of Iran's elite Quds Force of the Islamic Revolutionary Guards Corps, was killed in an American drone strike in January 2020.

The Pentagon has abruptly sent the aircraft carrier Nimitz home from the Middle East and Africa over the objections of top military advisers, marking a reversal of a weekslong muscle-flexing strategy aimed at deterring Iran from attacking American troops and diplomats in the Persian Gulf. Officials said on Friday that the acting defense secretary, Christopher C. Miller, had ordered the redeployment of the ship in part as a "de-escalatory" signal to Tehran to avoid stumbling into a crisis in President Trump's waning days in office. American intelligence reports indicate that Iran and its proxies may be preparing a strike as early as this weekend to avenge the death of Maj. Senior Pentagon officials said that Mr. Miller assessed that dispatching the Nimitz now, before the first anniversary this Sunday of General Suleimani's death in an American drone strike in Iraq, could remove what Iranian hard-liners see as a provocation that justifies their threats against American military targets. Some analysts said the return of the Nimitz to its home port of Bremerton, Wash., was a welcome reduction in tensions between the two countries.

Semantic segmentation models based on convolutional neural networks (CNNs) have gained much attention in relation to remote sensing and have achieved remarkable performance for the extraction of buildings from high-resolution aerial images. However, the issue of limited generalization for unseen images remains. When there is a domain gap between the training and test datasets, CNN-based segmentation models trained by a training dataset fail to segment buildings for the test dataset. In this paper, we propose segmentation networks based on a domain adaptive transfer attack (DATA) scheme for building extraction from aerial images. The proposed system combines the domain transfer and adversarial attack concepts. Based on the DATA scheme, the distribution of the input images can be shifted to that of the target images while turning images into adversarial examples against a target network. Defending adversarial examples adapted to the target domain can overcome the performance degradation due to the domain gap and increase the robustness of the segmentation model. Cross-dataset experiments and the ablation study are conducted for the three different datasets: the Inria aerial image labeling dataset, the Massachusetts building dataset, and the WHU East Asia dataset. Compared to the performance of the segmentation network without the DATA scheme, the proposed method shows improvements in the overall IoU. Moreover, it is verified that the proposed method outperforms even when compared to feature adaptation (FA) and output space adaptation (OSA).