Accurate morphometric assessment of cartilage-such as thickness/volume-via MRI is essential for monitoring knee osteoarthritis. Segmenting cartilage remains challenging and dependent on extensive expert-annotated datasets, which are heavily subjected to inter-reader variability. Recent advancements in Visual Foundational Models (VFM), especially memory-based approaches, offer opportunities for improving generalizability and robustness. This study introduces a deep learning (DL) method for cartilage and meniscus segmentation from 3D MRIs using interactive, memory-based VFMs. To improve spatial awareness and convergence, we incorporated a Hybrid Shuffling Strategy (HSS) during training and applied a segmentation mask propagation technique to enhance annotation efficiency. We trained four AI models-a CNN-based 3D-VNet, two automatic transformer-based models (SaMRI2D and SaMRI3D), and a transformer-based promptable memory-based VFM (SAMRI-2)-on 3D knee MRIs from 270 patients using public and internal datasets and evaluated on 57 external cases, including multi-radiologist annotations and different data acquisitions. Model performance was assessed against reference standards using Dice Score (DSC) and Intersection over Union (IoU), with additional morphometric evaluations to further quantify segmentation accuracy. SAMRI-2 model, trained with HSS, outperformed all other models, achieving an average DSC improvement of 5 points, with a peak improvement of 12 points for tibial cartilage. It also demonstrated the lowest cartilage thickness errors, reducing discrepancies by up to threefold. Notably, SAMRI-2 maintained high performance with as few as three user clicks per volume, reducing annotation effort while ensuring anatomical precision. This memory-based VFM with spatial awareness offers a novel approach for reliable AI-assisted knee MRI segmentation, advancing DL in musculoskeletal imaging.

In this paper we present the results of an evaluation study of the perfor-mance of LLMs on Technical Language Processing tasks. Humans are often confronted with tasks in which they have to gather information from dispar-ate sources and require making sense of large bodies of text. These tasks can be significantly complex for humans and often require deep study including rereading portions of a text. Towards simplifying the task of gathering in-formation we evaluated LLMs with chat interfaces for their ability to provide answers to standard questions that a human can be expected to answer based on their reading of a body of text. The body of text under study is Title 47 of the United States Code of Federal Regulations (CFR) which describes regula-tions for commercial telecommunications as governed by the Federal Com-munications Commission (FCC). This has been a body of text of interest be-cause our larger research concerns the issue of making sense of information related to Wireless Spectrum Governance and usage in an automated manner to support Dynamic Spectrum Access. The information concerning this wireless spectrum domain is found in many disparate sources, with Title 47 of the CFR being just one of many. Using a range of LLMs and providing the required CFR text as context we were able to quantify the performance of those LLMs on the specific task of answering the questions below.

Query expansion has been proved to be effective in improving recall and precision of first-stage retrievers, and yet its influence on a complicated, state-of-the-art cross-encoder ranker remains under-explored. We first show that directly applying the expansion techniques in the current literature to state-of-the-art neural rankers can result in deteriorated zero-shot performance. To this end, we propose GFF, a pipeline that includes a large language model and a neural ranker, to Generate, Filter, and Fuse query expansions more effectively in order to improve the zero-shot ranking metrics such as nDCG@10. Specifically, GFF first calls an instruction-following language model to generate query-related keywords through a reasoning chain. Leveraging self-consistency and reciprocal rank weighting, GFF further filters and combines the ranking results of each expanded query dynamically. By utilizing this pipeline, we show that GFF can improve the zero-shot nDCG@10 on BEIR and TREC DL 2019/2020. We also analyze different modelling choices in the GFF pipeline and shed light on the future directions in query expansion for zero-shot neural rankers.

Pre-trained large language models (LLMs) have recently achieved better generalization and sample efficiency in autonomous web automation. However, the performance on real-world websites has still suffered from (1) open domainness, (2) limited context length, and (3) lack of inductive bias on HTML. We introduce WebAgent, an LLM-driven agent that learns from self-experience to complete tasks on real websites following natural language instructions. WebAgent plans ahead by decomposing instructions into canonical sub-instructions, summarizes long HTML documents into task-relevant snippets, and acts on websites via Python programs generated from those. We design WebAgent with Flan-U-PaLM, for grounded code generation, and HTML-T5, new pre-trained LLMs for long HTML documents using local and global attention mechanisms and a mixture of long-span denoising objectives, for planning and summarization. We empirically demonstrate that our modular recipe improves the success on real websites by over 50%, and that HTML-T5 is the best model to solve various HTML understanding tasks; achieving 18.7% higher success rate than the prior method on MiniWoB web automation benchmark, and SoTA performance on Mind2Web, an offline task planning evaluation.

We are looking for a Senior NLP/ML Engineer to join our team. As a member of the Engineering team, you will work closely with other data scientists and software engineers as a key player in designing and building state-of-the-art ML decision systems for insurance claim processing. Work at Exadel - Who We Are: Since 1998, Exadel has been engineering its own software products and custom software for clients of all sizes. Headquartered in Walnut Creek, California, Exadel currently has 2700 employees in development centers across the Americas, Europe, and Asia. Our people drive Exadel's success, and they are at the core of our values.

Even in inflationary times, commissaries, supermarkets and other places where food is made or sold are increasingly turning to Artificial Intelligence and Machine Learning technologies to help them streamline operations, improve the customer experience, reduce waste and give their bottom lines a boost. San Ramon, Calif.-based AI and ML specialist Impulse Logic delivers advanced predictive analytics to create the optimal product flow through a retailer's store to optimize labor availability, ensure product availability, reduce waste, and increase profits, said Matt Frost, the company's CEO. "By optimizing the journey from warehouse to shop floor, stores can improve the way they manage their inventory to drive sales," Frost said. "Our innovative AI and ML-based solution does this by reading in-store data every two seconds." That ensures that store associates can make decisions based on accurate insights and ultimately deliver outstanding customer service and satisfaction.

Output of an Artificial Intelligence system from Google Vision, performing Facial Recognition on a ... [ ] photograph of a man, with facial features identified and facial bounding boxes present, San Ramon, California, November 22, 2019. A Google artificial intelligence tool will no longer identify photos with gender descriptions such as "man" or "woman," Business Insider reported. "Given that a person's gender cannot be inferred by appearance, we have decided to remove these labels in order to align with the Artificial Intelligence Principles at Google," the company said in an email to developers Thursday morning, according to Business Insider. Google's Cloud Vision API is a service that allows developers to attach labels to photos identifying the contents. It can detect faces, brand logos and other images. Bias in artificial intelligence has been increasingly controversial as use of the technology increases, said Business Insider.

Alison Stribling has learned a lot about infectious disease since she transferred onto Covid-19 response at the health department in Contra Costa County near San Francisco. One of her discoveries: How vital fax machines are to US pandemic response. Across the country, labs and health providers report new Covid-19 cases to local health departments. At Contra Costa Health Services, officials use the data to start contact tracing or send extra help in certain cases, such as at a care home or to an infected health care worker. On a typical day in Contra Costa, only around half of those reports arrive electronically; the rest, as many as hundreds, flow in via the fax line, creating a Sisyphean reading list.

SAN RAMON, California – Tesla is working on new battery technology that CEO Elon Musk says will enable the company within the next three years to make sleeker, more affordable cars that can travel dramatically longer distances on a single charge. But the battery breakthroughs that Musk unveiled Tuesday at a highly anticipated event didn't impress investors. They were hoping Tesla's technology would mark an even bigger leap forward and propel the company's soaring stock to even greater heights. Tesla's shares shed more than 6 percent in extended trading after Musk's presentation. That deepened a downturn that began during Tuesday's regular trading session as investors began to brace for a potential letdown.

To get ahead of such blazes, fire department officials in the Bay Area's Contra Costa County intentionally set four test fires of their own this summer. Each was surrounded by a set of field sensors capable of measuring temperature and humidity. When the initial ignition was detected, the sensors relayed the location of the blaze to a remote dashboard created by Zonehaven, a cloud-based analytics application that incorporate current weather conditions to devise a simulation of how quickly the fire would spread over the next five to 10 hours, and, if left unstopped, what nearby areas would be most at risk. The application is capable of sending out an immediate alert about an ignition situation to firefighters and local governments--anyone who needs instant information to start battling the blaze and plan evacuations. As you can see in the video below, the concept is being developed with the cooperation of the nearby Moraga-Orinda fire district, which battled California's deadly Rim and Camp fires in recent years.