Novel categories names:['High_Jump', 'Front_Crawl', 'Pole_V ault', 'Hammer_Throw', All experiments are conducted under the 16-shot setting. An incremental bayesian approach tested on 101 object categories. Conditional prompt learning for vision-language models.

Datasets of complex cyber-physical systems (CPS) are difficult to build and large CPS datasets are not publicly available.

Dermnet-S chooses the top-30 classes for meta-training.

SINGAPORE - Several U.S. drone firms made their debuts at the Singapore Airshow this week, seeking to expand their business beyond the Pentagon to countries in Asia that are increasingly concerned about the threat posed by China's military buildup. The lethal success of drones on both sides of Russia's war in Ukraine has sparked a surge of Silicon Valley investment in drone and military artificial intelligence startups, boosting the valuations of U.S. firms like California-based Anduril Industries and Shield AI. This wave of interest in the next generation of warfare is reshaping the character of major air shows that have been long-dominated by gleaming commercial airliners, daredevil fighter jets and troop-carrying helicopters. In a time of both misinformation and too much information, quality journalism is more crucial than ever. By subscribing, you can help us get the story right. With your current subscription plan you can comment on stories.

High-altitude platforms could help connect over 2 billion people around the world who are still offline. Today, an estimated 2.2 billion people But that number could drop this year, thanks to tests of stratospheric airships, uncrewed aircraft, and other high-altitude platforms for internet delivery. Even with nearly 10,000 active Starlink satellites in orbit and the OneWeb constellation of 650 satellites, solid internet coverage is not a given across vast swathes of the planet. One of the most prominent efforts to plug the connectivity gap was Google X's Loon project . Launched in 2011, it aimed to deliver access using high-altitude balloons stationed above predetermined spots on Earth. But the project faced literal headwinds--the Loons kept drifting away and new ones had to be released constantly, making the venture economically unfeasible.

Reinforcement learning (RL) demonstrates superior potential over traditional flight control methods for fixed-wing aircraft, particularly under extreme operational conditions. However, the high demand for training samples and the lack of efficient computation in existing simulators hinder its further application. In this paper, we introduce NeuralPlane, the first benchmark platform for large-scale parallel simulations of fixed-wing aircraft. NeuralPlane significantly boosts high-fidelity simulation via GPU-accelerated Flight Dynamics Model (FDM) computation, achieving a single-step simulation time of just 0.2 seconds at a parallel scale of $10^{6}$, far exceeding current platforms. We also provide clear code templates, comprehensive evaluation/visualization tools and hierarchical frameworks for integrating RL and traditional control methods. We believe that NeuralPlane can accelerate the development of RL-based fixed-wing flight control and serve as a new challenging benchmark for the RL community.

We consider the problem of controlling an unknown stochastic linear system with quadratic costs -- called the adaptive LQ control problem. We re-examine an approach called ``Reward-Biased Maximum Likelihood Estimate'' (RBMLE) that was proposed more than forty years ago, and which predates the ``Upper Confidence Bound'' (UCB) method, as well as the definition of ``regret'' for bandit problems. It simply added a term favoring parameters with larger rewards to the criterion for parameter estimation. We show how the RBMLE and UCB methods can be reconciled, and thereby propose an Augmented RBMLE-UCB algorithm that combines the penalty of the RBMLE method with the constraints of the UCB method, uniting the two approaches to optimism in the face of uncertainty. We establish that theoretically, this method retains ${\mathcal{O}}(\sqrt{T})$ regret, the best known so far. We further compare the empirical performance of the proposed Augmented RBMLE-UCB and the standard RBMLE (without the augmentation) with UCB, Thompson Sampling, Input Perturbation, Randomized Certainty Equivalence and StabL on many real-world examples including flight control of Boeing 747 and Unmanned Aerial Vehicle. We perform extensive simulation studies showing that the Augmented RBMLE consistently outperforms UCB, Thompson Sampling and StabL by a huge margin, while it is marginally better than Input Perturbation and moderately better than Randomized Certainty Equivalence.