Short-video platforms have rapidly become a new generation of information retrieval systems, where users formulate queries to access desired videos. However, user queries, especially long-tail ones, often suffer from spelling errors, incomplete phrasing, and ambiguous intent, resulting in mismatches between user expectations and retrieved results. While large language models (LLMs) have shown success in long-tail query rewriting within e-commerce, they struggle on short-video platforms, where proprietary content such as short videos, live streams, micro dramas, and user social networks falls outside their training distribution. To address this challenge, we introduce \textbf{CardRewriter}, an LLM-based framework that incorporates domain-specific knowledge to enhance long-tail query rewriting. For each query, our method aggregates multi-source knowledge relevant to the query and summarizes it into an informative and query-relevant knowledge card. This card then guides the LLM to better capture user intent and produce more effective query rewrites. We optimize CardRewriter using a two-stage training pipeline: supervised fine-tuning followed by group relative policy optimization, with a tailored reward system balancing query relevance and retrieval effectiveness. Offline experiments show that CardRewriter substantially improves rewriting quality for queries targeting proprietary content. Online A/B testing further confirms significant gains in long-view rate (LVR) and click-through rate (CTR), along with a notable reduction in initiative query reformulation rate (IQRR). Since September 2025, CardRewriter has been deployed on Kuaishou, one of China's largest short-video platforms, serving hundreds of millions of users daily.

By design, large language models (LLMs) are static general-purpose models, expensive to retrain or update frequently. As they are increasingly adopted for knowledge-intensive tasks, it becomes evident that these design choices lead to failures to generate factual, relevant, and up-to-date knowledge. To this end, we propose \ourmethod{}, a modular framework to plug in new factual and relevant knowledge into general-purpose LLMs. We first introduce \emph{knowledge cards} -- specialized language models trained on corpora from specific domains and sources. Knowledge cards serve as parametric repositories that are selected at inference time to generate background knowledge for the base LLM. We then propose three content selectors to dynamically select and retain information in documents generated by knowledge cards, specifically controlling for \emph{relevance}, \emph{brevity}, and \emph{factuality} of outputs. Finally, we propose two complementary integration approaches to augment the base LLM with the (relevant, factual) knowledge curated from the specialized LMs. Through extensive experiments, we demonstrate that \ourmethod{} achieves state-of-the-art performance on six benchmark datasets. Ultimately, \ourmethod{} framework enables dynamic synthesis and updates of knowledge from diverse domains. Its modularity will ensure that relevant knowledge can be continuously updated through the collective efforts of the research community.

Nowadays cross-industry ranging challenges include the reduction of greenhouse gas emission and enabling a circular economy. However, the production of paper from waste paper is still a highly resource intensive task, especially in terms of energy consumption. While paper machines produce a lot of data, we have identified a lack of utilization of it and implement a concept using an operator assistance system and state-of-the-art machine learning techniques, e.g., classification, forecasting and alarm flood handling algorithms, to support daily operator tasks. Our main objective is to provide situation-specific knowledge to machine operators utilizing available data. We expect this will result in better adjusted parameters and therefore a lower footprint of the paper machines.

Google and other search engines feature the entity search by representing a knowledge card summarizing related facts about the user-supplied entity. However, the knowledge card is limited to certain entities that have a Wiki page or an entry in encyclopedias such as Freebase. The current encyclopedias are limited to highly popular entities, which are far fewer compared with the emerging entities. Despite the availability of knowledge about the emerging entities on the search results, yet there are no approaches to capture, abstract, summerize, fuse, and validate fragmented pieces of knowledge about them. Thus, in this paper, we develop approaches to capture two types of knowledge about the emerging entities from a corpus extended from top-n search snippets of a given emerging entity. The first kind of knowledge identifies the role(s) of the emerging entity as, e.g., who is s/he? The second kind captures the entities closely associated with the emerging entity. As the testbed, we considered a collection of 20 emerging entities and 20 popular entities as the ground truth. Our approach is an unsupervised approach based on text analysis and entity embeddings. Our experimental studies show promising results as the accuracy of more than $87\%$ for recognizing entities and $75\%$ for ranking them. Besides $87\%$ of the entailed types were recognizable. Our testbed and source code is available on Github https://github.com/sunnyUD/research_source_code.

This paper develops the concept of knowledge and its exchange using Semantic Web technologies. It points out that knowledge is more than information because it embodies the meaning, that is to say semantic and context. These characteristics will influence our approach to represent and to treat the knowledge. In order to be adopted, the developed system needs to be simple and to use standards. The goal of the paper is to find standards to model knowledge and exchange it with an other person. Therefore, we propose to model knowledge using UML models to show a graphical representation and to exchange it with XML to ensure the portability at low cost. We introduce the concept of ontology for organizing knowledge and for facilitating the knowledge exchange. Proposals have been tested by implementing an application on the design knowledge of a pen.

Google has today launched a re-imagined version of its free Earth mapping service, weaving in storytelling and artificial intelligence. The new programme lets people get a close-up look of the planet from the comfort of their computers, smartphones or tablets. The new-look Google Earth enables its users to learn about far-flung corners of the globe under the guidance of scientists from Nasa and prestigious research institutions. Google Earth's new start-up screen offers a global view of the Earth. 'This is our gift to the world,' Google Earth director Rebecca Moore said.