Entity Linking (EL) is the process of associating ambiguous textual mentions to specific entities in a knowledge base. Traditional EL methods heavily rely on large datasets to enhance their performance, a dependency that becomes problematic in the context of few-shot entity linking, where only a limited number of examples are available for training. To address this challenge, we present OneNet, an innovative framework that utilizes the few-shot learning capabilities of Large Language Models (LLMs) without the need for fine-tuning. To the best of our knowledge, this marks a pioneering approach to applying LLMs to few-shot entity linking tasks. OneNet is structured around three key components prompted by LLMs: (1) an entity reduction processor that simplifies inputs by summarizing and filtering out irrelevant entities, (2) a dual-perspective entity linker that combines contextual cues and prior knowledge for precise entity linking, and (3) an entity consensus judger that employs a unique consistency algorithm to alleviate the hallucination in the entity linking reasoning. Comprehensive evaluations across seven benchmark datasets reveal that OneNet outperforms current state-of-the-art entity linking methods.

We provide an integrated and systematic automation approach to spatial object recognition and positional detection using AI machine learning and computer vision algorithms for Orange County, California. We describe a comprehensive methodology for multi-sensor, high-resolution field data acquisition, along with post-field processing and pre-analysis processing tasks. We developed a series of algorithmic formulations and workflows that integrate convolutional deep neural network learning with detected object positioning estimation in 360{\deg} equirectancular photosphere imagery. We provide examples of application processing more than 800 thousand cardinal directions in photosphere images across two areas in Orange County, and present detection results for stop-sign and fire hydrant object recognition. We discuss the efficiency and effectiveness of our approach, along with broader inferences related to the performance and implications of this approach for future technological innovations, including automation of spatial data and public asset inventories, and near real-time AI field data systems.

An important problem in forensic analyses is identifying the provenance of materials at a crime scene, such as biological material on a piece of clothing. This procedure, known as geolocation, is conventionally guided by expert knowledge of the biological evidence and therefore tends to be application-specific, labor-intensive, and subjective. Purely data-driven methods have yet to be fully realized due in part to the lack of a sufficiently rich data source. However, high-throughput sequencing technologies are able to identify tens of thousands of microbial taxa using DNA recovered from a single swab collected from nearly any object or surface. We present a new algorithm for geolocation that aggregates over an ensemble of deep neural network classifiers trained on randomly-generated Voronoi partitions of a spatial domain. We apply the algorithm to fungi present in each of 1300 dust samples collected across the continental United States and then to a global dataset of dust samples from 28 countries. Our algorithm makes remarkably good point predictions with more than half of the geolocation errors under 100 kilometers for the continental analysis and nearly 90% classification accuracy of a sample's country of origin for the global analysis. We suggest that the effectiveness of this model sets the stage for a new, quantitative approach to forensic geolocation.

Imagine a world where you can sit next to your customers and have a one on one conversation about their expectations from your brand with every interaction, and deliver on their expectations Every. Seems like a utopian dream? As we move forward in the digital era, this might be the reality for the brands, where businesses get the opportunity to win their customers' heart with every single interaction. The evolving technologies are opening up such opportunities for brands, and these opportunities will only increase as these technologies evolve. Smartphone is the magic wand which will make this dream a reality for brands and new-age technologies will power this magic wand.

Concerned that all discussion of computers focused on technology, Kling studied government, manufacturers and insurance companies to determine how computers affect society and require choices that consider human values as well as technological values. In his prolific writings and speeches, Kling often used analogies to the automobile to make his esoteric topic more easily understood. Technological debates could be likened to discussing the latest sports car model, he told The Times in 1992, while informatics addresses how the automobile has affected society, including construction of highways and development of suburbs. Kling's studies convinced him that "there is an underside to computer technology," he said. For example, he said that organizations often fail to train employees properly in computer use, making the task a "hassle and a cause of stress" and that dependency on computers for communication eliminates creative, stimulating social interaction.