Estimating disease severity from endoscopic images is essential in assessing ulcerative colitis, where the Mayo Endoscopic Subscore (MES) is widely used to grade inflammation. However, MES classification remains challenging due to label noise from inter-observer variability and the ordinal nature of the score, which standard models often ignore. We propose CLoE, a curriculum learning framework that accounts for both label reliability and ordinal structure. Image quality, estimated via a lightweight model trained on Boston Bowel Preparation Scale (BBPS) labels, is used as a proxy for annotation confidence to order samples from easy (clean) to hard (noisy). This curriculum is further combined with ResizeMix augmentation to improve robustness. Experiments on the LIMUC and HyperKvasir datasets, using both CNNs and Transformers, show that CLoE consistently improves performance over strong supervised and self-supervised baselines. For instance, ConvNeXt-Tiny reaches 82.5\% accuracy and a QWK of 0.894 on LIMUC with low computational cost. These results highlight the potential of difficulty-aware training strategies for improving ordinal classification under label uncertainty. Code will be released at https://github.com/zeynepozdemir/CLoE.

Densify, a company that helps enterprises make sure that they're using their compute resources to the fullest extent possible, announced a new service today that uses AI to cut down customers' cloud bills. The Cloud Learning Optimization Engine (Cloe for short) analyzes workloads using machine learning to determine how much CPU, RAM, and storage they need, then suggests ways to save money. Cloe has helped customers like Bank of America, Honda, and IBM save an average of 40 percent on their cloud bills, with some customers seeing savings of more than 80 percent. After analyzing the needs of each workload, it suggests compute instances companies can shut down, workloads that can sit on the same instance to save money, and ways to optimize which types of virtual machines customers use in order to reduce their spend. As more companies move their workloads to the public cloud, the sort of optimization work that Cloe helps with is an important component of ensuring that businesses aren't spending too much on their computing infrastructure.

In the 'Big Data' era, many real-world applications like search involve the ranking problem for a large number of items. It is important to obtain effective ranking results and at the same time obtain the results efficiently in a timely manner for providing good user experience and saving computational costs. Valuable prior research has been conducted for learning to efficiently rank like the cascade ranking (learning) model, which uses a sequence of ranking functions to progressively filter some items and rank the remaining items. However, most existing research of learning to efficiently rank in search is studied in a relatively small computing environments with simulated user queries. This paper presents novel research and thorough study of designing and deploying a Cascade model in a Large-scale Operational E-commerce Search application (CLOES), which deals with hundreds of millions of user queries per day with hundreds of servers. The challenge of the real-world application provides new insights for research: 1). Real-world search applications often involve multiple factors of preferences or constraints with respect to user experience and computational costs such as search accuracy, search latency, size of search results and total CPU cost, while most existing search solutions only address one or two factors; 2). Effectiveness of e-commerce search involves multiple types of user behaviors such as click and purchase, while most existing cascade ranking in search only models the click behavior. Based on these observations, a novel cascade ranking model is designed and deployed in an operational e-commerce search application. An extensive set of experiments demonstrate the advantage of the proposed work to address multiple factors of effectiveness, efficiency and user experience in the real-world application.

Remember those charming smartphone ads a few years ago where people held conversations with Siri, Apple iOS' enchanting virtual assistant? The concept was innovative for operating the phone hands-free but not so helpful in searching the web on your behalf. Oftentimes, Siri comes up with entirely wrong answers, too many options or services only tangentially relevant to your inquiry. Asking for a modestly-priced tailor or an upscale sushi bar known for uni is too ambitious. She hears us, but she's not listening.