Jeff Bezos likes to surprise. Roaming Amazon's global headquarters in 2013, the tycoon promised a television crew half his fortune if they could guess his company's latest innovation. "Oh my God," one of his wide-eyed guests exclaimed, as they caught sight of autonomous delivery drones. Bezos, a self-declared optimist, suggested it could happen by 2017, or maybe 2018. "I know this looks like science fiction. It's not," he told 60 Minutes on CBS in 2013.

Tracking of inventory and rearrangement of misplaced items are some of the most labor-intensive tasks in a retail environment. While there have been attempts at using vision-based techniques for these tasks, they mostly use planogram compliance for detection of any anomalies, a technique that has been found lacking in robustness and scalability. Moreover, existing systems rely on human intervention to perform corrective actions after detection. In this paper, we present Co-AD, a Concept-based Anomaly Detection approach using a Vision Transformer (ViT) that is able to flag misplaced objects without using a prior knowledge base such as a planogram. It uses an auto-encoder architecture followed by outlier detection in the latent space. Co-AD has a peak success rate of 89.90% on anomaly detection image sets of retail objects drawn from the RP2K dataset, compared to 80.81% on the best-performing baseline of a standard ViT auto-encoder. To demonstrate its utility, we describe a robotic mobile manipulation pipeline to autonomously correct the anomalies flagged by Co-AD. This work is ultimately aimed towards developing autonomous mobile robot solutions that reduce the need for human intervention in retail store management.

Supply chain management (SCM) has been recognized as an important discipline with applications to many industries, where the two-echelon stochastic inventory model, involving one downstream retailer and one upstream supplier, plays a fundamental role for developing firms' SCM strategies. In this work, we aim at designing online learning algorithms for this problem with an unknown demand distribution, which brings distinct features as compared to classic online optimization problems. Specifically, we consider the two-echelon supply chain model introduced in [Cachon and Zipkin, 1999] under two different settings: the centralized setting, where a planner decides both agents' strategy simultaneously, and the decentralized setting, where two agents decide their strategy independently and selfishly. We design algorithms that achieve favorable guarantees for both regret and convergence to the optimal inventory decision in both settings, and additionally for individual regret in the decentralized setting. Our algorithms are based on Online Gradient Descent and Online Newton Step, together with several new ingredients specifically designed for our problem. We also implement our algorithms and show their empirical effectiveness.

Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. This risk motivates safety efforts such as red-teaming and large-scale feedback learning, which aim to make models both helpful and harmless. However, there is a tension between these two objectives, since harmlessness requires models to refuse to comply with unsafe prompts, and thus not be helpful. Recent anecdotal evidence suggests that some models may have struck a poor balance, so that even clearly safe prompts are refused if they use similar language to unsafe prompts or mention sensitive topics. In this paper, we introduce a new test suite called XSTest to identify such eXaggerated Safety behaviours in a systematic way. XSTest comprises 250 safe prompts across ten prompt types that well-calibrated models should not refuse to comply with, and 200 unsafe prompts as contrasts that models, for most applications, should refuse. We describe XSTest's creation and composition, and then use the test suite to highlight systematic failure modes in state-of-the-art language models as well as more general challenges in building safer language models.

CyberGuy explains how Walmart is using artificial intelligence to enhance the shopping experience. You might be tempted to buy products on Amazon that have glowing reviews and high ratings. After all, who doesn't want to get the best deal possible? Before you click that "buy now" button, you might want to take a closer look at those reviews. Because, as it turns out, not all of them are genuine.

CyberGuy explains how Walmart is using artificial intelligence to enhance the shopping experience. Walmart, the world's largest retailer, is using artificial intelligence to transform how we shop. The retailer is not only using generative AI to automate its office tasks but also to improve its customer service and the way we discover and see products. Walmart launched a generative AI app for its office workers in August. The app, called "My Assistant," can help employees with various tasks, such as scheduling meetings, booking travel, ordering supplies and generating reports.

Amazon's October Prime Day sale officially ended on Wednesday, but a few of the deals are still live as we head into the weekend. If you were hoping to check off a few more names from your holiday gift list or buy something for yourself at a discount, see what remains on sale below. We combed through our coverage over the past few days to find the best of what's left. While Amazon has returned most of their own devices, like Echos and Kindles, back to their full prices, a handful of products from other brands like Google, Samsung and Anker, have maintained the lows they hit on Prime Day. Here are the best deals from Prime Big Deal Days that you can still get right now. Samsung's flagship smartwatch hasn't been available long but can be picked up at a $30 discount.

Amazon's October Prime Day sale officially ended yesterday, but some of the deals are still live. That means there's time to run through your holiday gift list one more time or pick up something for yourself at a discount. We combed through our coverage over the past few days to find the best sales still available today. Amazon has returned most of their own devices, like Echos and Kindles, back to their full prices. But products from other brands, notably Google, Samsung and Anker, have maintained the same lows they hit on Prime Day. Here are the best deals from Prime Big Deal Days that you can still get right now.

Major retailers in the US are already using facial recognition cameras to spy on shoppers, a campaigning group has warned. The tech - usually associated with authoritative regimes like China - is being used both to identify shoplifters and serve'personalized' adverts. Caitlin Seeley George of anti-face recognition campaign group Fight for the Future told DailyMail.com Walgreens and Macy's are among the largest retailers to adopt the technology, deploying it in hundreds of stores across the country. And it is not just America - Britain is also adopting the tech.

We've reached the last day of Amazon's October Prime Day sale and if you're in the market for some deals that won't break the bank, here are 29 deals that are all under $50. We've found plenty of the less expensive gadgets that we've tested and tried recently. Many, like the JOBY Gorillapod and the JBL Go 3 make excellent stocking stuffers, and there are deals on smart plugs (for indoors and out) that will make your holiday light management far simpler. Amazon is surfacing strong deals on its own Echo smart speakers and Fire TV sticks. Plus you'll find iPhone accessories, chargers, smart home devices which not only make nice gifts for the hard-to-shop-for, they're nice to keep for yourself too.