Abstract-- In this paper, we study the problem of generating low-altitude path plans for nap-of-the-earth (NOE) flight in real time with only RGB images from onboard cameras and the vehicle pose. We propose a novel training method that combines behavior cloning and self-supervised learning, where the self-supervision component allows the learned policy to refine the paths generated by the expert planner . Nap-of-the-earth (NOE) flight is an important tactic to reduce the exposure of an aircraft during flights. For a piloted aircraft flying at high speed, NOE flights are intensive as they require the pilots to extract terrain information and react very quickly to new information. Therefore, it would be beneficial to automate some of the tasks, such as path planning [1]. Moreover, solutions relying only on sensors that do not emit (e.g. Automating part of the navigation task for NOE flights has been studied in numerous previous works.

Vascular anastomosis, the surgical connection of blood vessels, is essential in procedures such as organ transplants and reconstructive surgeries. The precision required limits accessibility due to the extensive training needed, with manual suturing leading to variable outcomes and revision rates up to 7.9%. Existing robotic systems, while promising, are either fully teleoperated or lack the capabilities necessary for autonomous vascular anastomosis. We present the Micro Smart Tissue Autonomous Robot (micro-STAR), an autonomous robotic system designed to perform vascular anastomosis on small-diameter vessels. The micro-STAR system integrates a novel suturing tool equipped with Optical Coherence Tomography (OCT) fiber-optic sensor and a microcamera, enabling real-time tissue detection and classification. Our system autonomously places sutures and manipulates tissue with minimal human intervention. In an ex vivo study, micro-STAR achieved outcomes competitive with experienced surgeons in terms of leak pressure, lumen reduction, and suture placement variation, completing 90% of sutures without human intervention. This represents the first instance of a robotic system autonomously performing vascular anastomosis on real tissue, offering significant potential for improving surgical precision and expanding access to high-quality care.

LLM have achieved success in many fields but still troubled by problematic content in the training corpora. LLM unlearning aims at reducing their influence and avoid undesirable behaviours. However, existing unlearning methods remain vulnerable to adversarial queries and the unlearned knowledge resurfaces after the manually designed attack queries. As part of a red-team effort to proactively assess the vulnerabilities of unlearned models, we design Dynamic Unlearning Attack (DUA), a dynamic and automated framework to attack these models and evaluate their robustness. It optimizes adversarial suffixes to reintroduce the unlearned knowledge in various scenarios. We find that unlearned knowledge can be recovered in $55.2\%$ of the questions, even without revealing the unlearned model's parameters. In response to this vulnerability, we propose Latent Adversarial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process. It formulates the unlearning process as a min-max optimization problem and resolves it through two stages: an attack stage, where perturbation vectors are trained and added to the latent space of LLMs to recover the unlearned knowledge, and a defense stage, where previously trained perturbation vectors are used to enhance unlearned model's robustness. With our LAU framework, we obtain two robust unlearning methods, AdvGA and AdvNPO. We conduct extensive experiments across multiple unlearning benchmarks and various models, and demonstrate that they improve the unlearning effectiveness by over $53.5\%$, cause only less than a $11.6\%$ reduction in neighboring knowledge, and have almost no impact on the model's general capabilities.

Syft, a leading national provider of healthcare inventory control and end-to-end supply chain cost management software and services, today announced new artificial intelligence (AI) capabilities in its Syft Synergy Platform 4.1. The AI algorithms in the supply chain software enable procedural level decision support metrics on costs and variance data linked to patient outcomes. Almost all (98 percent) of healthcare executives surveyed earlier this year say supply chain management is a moderate to high priority and 97 percent believe supply chain analytics can positively impact costs.1 However, many hospitals and health systems today are not equipped to optimize their supply chains, relying on standard statistical approaches that may use homegrown spreadsheets to analyze procedure supply costs, identify outliers, and forecast demand. And, while value-based care programs such as the Bundled Payments for Care Initiative-Advanced (BCPI-A) make it imperative for health systems to know their costs, most hospitals today are unable to identify their true cost per case or analyze their cost variances by surgeon, procedure of specialty.

Most people have heard about self-driving cars, with companies from Google to Honda developing autonomous vehicles. But driverless technology could be going beyond cars, with the testing of a self-flying helicopter. A Sikorsky S-76 commercial helicopter has now successfully taken off and flown autonomously 30 miles, before landing itself safely. The helicopter in the trial was the Sikorsky S-76 model which used Sikorsky's MATRIX system The Sikorsky Autonomy Research Aircraft (SARA), used Sikorsky's MATRIX system. This is the same system that is use in the Optionally Piloted Black Hawk (OPBH) Demonstrator.

Most people have heard about self-driving cars, with companies from Google to Honda developing autonomous vehicles. But driverless technology could be going beyond cars, with the testing of a self-flying helicopter. A Sikorsky S-76 commercial helicopter has now successfully taken off and flown autonomously 30 miles, before landing itself safely. The helicopter in the trial was the Sikorsky S-76 model which used Sikorsky's MATRIX system The Sikorsky Autonomy Research Aircraft (SARA), used Sikorsky's MATRIX system. This is the same system that is use in the Optionally Piloted Black Hawk (OPBH) Demonstrator.

Most people have heard about self-driving cars, with companies from Google to Honda developing autonomous vehicles. But driverless technology could be going beyond cars, with the testing of a self-flying helicopter. A Sikorsky S-76 commercial helicopter has now successfully taken off and flown autonomously 30 miles, before landing itself safely. The helicopter in the trial was the Sikorsky S-76 model which used Sikorsky's MATRIX system The Sikorsky Autonomy Research Aircraft (SARA), used Sikorsky's MATRIX system. This is the same system that is use in the Optionally Piloted Black Hawk (OPBH) Demonstrator.