In the rapidly evolving landscape of digital content, the task of summarizing multimedia documents, which encompass textual, visual, and auditory elements, presents intricate challenges. These challenges include extracting pertinent information from diverse formats, maintaining the structural integrity and semantic coherence of the original content, and generating concise yet informative summaries. This paper introduces a novel framework for multimedia document summarization that capitalizes on the inherent structure of the document to craft coherent and succinct summaries. Central to this framework is the incorporation of a rhetorical structure for structural analysis, augmented by a graph-based representation to facilitate the extraction of pivotal information. Weighting algorithms are employed to assign significance values to document units, thereby enabling effective ranking and selection of relevant content. Furthermore, the framework is designed to accommodate user preferences and time constraints, ensuring the production of personalized and contextually relevant summaries. The summarization process is elaborately delineated, encompassing document specification, graph construction, unit weighting, and summary extraction, supported by illustrative examples and algorithmic elucidation. This proposed framework represents a significant advancement in automatic summarization, with broad potential applications across multimedia document processing, promising transformative impacts in the field.

While new technologies emerge, human errors always looming. Software supply chain is increasingly complex and intertwined, the security of a service has become paramount to ensuring the integrity of products, safeguarding data privacy, and maintaining operational continuity. In this work, we conducted experiments on the promising open Large Language Models (LLMs) into two main software security challenges: source code language errors and deprecated code, with a focus on their potential to replace conventional static and dynamic security scanners that rely on predefined rules and patterns. Our findings suggest that while LLMs present some unexpected results, they also encounter significant limitations, particularly in memory complexity and the management of new and unfamiliar data patterns. Despite these challenges, the proactive application of LLMs, coupled with extensive security databases and continuous updates, holds the potential to fortify Software Supply Chain (SSC) processes against emerging threats.

Machine learning systems increasingly drive innovation across scientific fields and industry, yet challenges in compute overhead, specifically during inference, limit their scalability and sustainability. Responsible AI guardrails, essential for ensuring fairness, transparency, and privacy, further exacerbate these computational demands. This study addresses critical gaps in the literature, chiefly the lack of generalized predictive techniques for latency and energy consumption, limited cross-comparisons of classifiers, and unquantified impacts of RAI guardrails on inference performance. Using Theory Construction Methodology, this work constructed a model-agnostic theoretical framework for predicting latency and energy consumption in binary classification models during inference. The framework synthesizes classifier characteristics, dataset properties, and RAI guardrails into a unified analytical instrument. Two predictive equations are derived that capture the interplay between these factors while offering generalizability across diverse classifiers. The proposed framework provides foundational insights for designing efficient, responsible ML systems. It enables researchers to benchmark and optimize inference performance and assists practitioners in deploying scalable solutions. Finally, this work establishes a theoretical foundation for balancing computational efficiency with ethical AI principles, paving the way for future empirical validation and broader applications.

Spherical Sliced-Wasserstein (SSW) has recently been proposed to measure the discrepancy between spherical data distributions in various fields, such as geology, medical domains, computer vision, and deep representation learning. However, in the original SSW, all projection directions are treated equally, which is too idealistic and cannot accurately reflect the importance of different projection directions for various data distributions. To address this issue, we propose a novel data-adaptive Discriminative Spherical Sliced-Wasserstein (DSSW) distance, which utilizes a projected energy function to determine the discriminative projection direction for SSW. In our new DSSW, we introduce two types of projected energy functions to generate the weights for projection directions with complete theoretical guarantees. The first type employs a non-parametric deterministic function that transforms the projected Wasserstein distance into its corresponding weight in each projection direction. This improves the performance of the original SSW distance with negligible additional computational overhead. The second type utilizes a neural network-induced function that learns the projection direction weight through a parameterized neural network based on data projections. This further enhances the performance of the original SSW distance with less extra computational overhead. Finally, we evaluate the performance of our proposed DSSW by comparing it with several state-of-the-art methods across a variety of machine learning tasks, including gradient flows, density estimation on real earth data, and self-supervised learning.

The detection of hate speech has become increasingly important in combating online hostility and its real-world consequences. Despite recent advancements, there is limited research addressing hate speech detection in Devanagari-scripted languages, where resources and tools are scarce. While large language models (LLMs) have shown promise in language-related tasks, traditional fine-tuning approaches are often infeasible given the size of the models. In this paper, we propose a Parameter Efficient Fine tuning (PEFT) based solution for hate speech detection and target identification. We evaluate multiple LLMs on the Devanagari dataset provided by (Thapa et al., 2025), which contains annotated instances in 2 languages - Hindi and Nepali. The results demonstrate the efficacy of our approach in handling Devanagari-scripted content.

Language models based on deep neural networks are vulnerable to textual adversarial attacks. While rich-resource languages like English are receiving focused attention, Tibetan, a cross-border language, is gradually being studied due to its abundant ancient literature and critical language strategy. Currently, there are several Tibetan adversarial text generation methods, but they do not fully consider the textual features of Tibetan script and overestimate the quality of generated adversarial texts. To address this issue, we propose a novel Tibetan adversarial text generation method called TSCheater, which considers the characteristic of Tibetan encoding and the feature that visually similar syllables have similar semantics. This method can also be transferred to other abugidas, such as Devanagari script. We utilize a self-constructed Tibetan syllable visual similarity database called TSVSDB to generate substitution candidates and adopt a greedy algorithm-based scoring mechanism to determine substitution order. After that, we conduct the method on eight victim language models. Experimentally, TSCheater outperforms existing methods in attack effectiveness, perturbation magnitude, semantic similarity, visual similarity, and human acceptance. Finally, we construct the first Tibetan adversarial robustness evaluation benchmark called AdvTS, which is generated by existing methods and proofread by humans.

Days after New Hampshire voters received a robocall with an artificially generated voice that resembled President Joe Biden's, the Federal Communications Commission banned the use of AI-generated voices in robocalls. The 2024 United States election would be the first to unfold amid wide public access to AI generators, which let people create images, audio and video – some for nefarious purposes. Institutions rushed to limit AI-enabled misdeeds. Sixteen states enacted legislation around AI's use in elections and campaigns; many of these states required disclaimers in synthetic media published close to an election. The Election Assistance Commission, a federal agency supporting election administrators, published an "AI toolkit" with tips election officials could use to communicate about elections in an age of fabricated information.

Testimony and several reports have exposed unidentified flying object (UFO) sightings across the country amid the national attention on apparent drone observations over recent weeks. Luiz Elizondo, the former head of the Defense Department's Advanced Aerospace Threat Identification Program, and other witnesses testified before Congress last month about an alleged government group "hid[ing] the fact that we are not alone in the cosmos." "I believe that we as Americans can handle the truth. And I also believe the world deserves the truth," Elizondo said, urging Congress to enact legislation protecting whistleblowers too afraid to come forward. This UFO was photographed when it hovered for 15 minutes near the Holloman Air Development Center in Alamogordo, N.M., on Dec. 16, 1957. The hearing was part of a larger effort by lawmakers to investigate UFOs, or unidentified aerial phenomenon (UAPs), and determine whether elements within the government are unlawfully withholding evidence from Congress.

Israeli troops and military aircraft have killed at least eight Palestinians, including two women and a teenager, in attacks on the Tulkarem and Nur Shams refugee camps in the occupied West Bank, the Palestinian Health Ministry said. Seven people were killed in an Israeli drone attack and shooting by troops in the Tulkarem refugee camp, and one person was killed in the nearby Nur Shams camp, the Health Ministry said, following a bloody day of Israeli military raids that began at dawn on Tuesday. The ministry said that two Palestinian women – identified as Khawla Ali Abdullah Abdo, 53, and Bara Khalid Hussein, 30 – and an 18-year-old, Fathi Saeed Salem Obaid, were among the seven people killed in the Israeli attacks on Tulkarem. The official Wafa news agency reported that the teenager died after being shot in the chest and abdomen and the two women were reported killed in drone strikes. The victim in the Nur Shams camp was identified as Mahmoud Muhammad Khaled Amar, who was shot by Israeli soldiers and later found dead on the ground in the camp's Abu Bakr as-Siddiq Mosque neighbourhood, Wafa also reports.

Hsinchu, Taiwan – A crane bird flies across a silent rice paddy, the water slowly trickling in the background. It is a tranquil and stereotypical image of an East-Asian countryside. Little seems to suggest I am just a few kilometres removed from one of the hearts of the global economy. This is Hsinchu, a small city close to Taipei in Taiwan. It is what you could literally call the Silicon Valley of the world.