Many real-world bandit applications are characterized by sparse rewards, which can significantly hinder learning efficiency. Leveraging problem-specific structures for careful distribution modeling is recognized as essential for improving estimation efficiency in statistics. However, this approach remains under-explored in the context of bandits. To address this gap, we initiate the study of zero-inflated bandits, where the reward is modeled using a classic semi-parametric distribution known as the zero-inflated distribution. We develop algorithms based on the Upper Confidence Bound and Thompson Sampling frameworks for this specific structure. The superior empirical performance of these methods is demonstrated through extensive numerical studies.

In complex multi-robot application scenarios, particularly in dynamically adversarial, hazardous, or disaster environments, traditional cooperation paradigms face significant challenges due to unreliable or absent communication links. Achieving efficient cooperation in the absence of communication has become a key bottleneck limiting the performance of multirobot systems. In this paper, we propose a Global Intent Prediction and Decomposition (GIPD) framework that enables robots to perform cooperative behavior without relying on communication. Each robot independently infers a globally consistent intent based solely on its local observations, ensuring implicit alignment across the system. Given the inferred global intent, robots autonomously determine their responsibilities and select the most appropriate tasks. They then base their local decision-making on the global intent, selected tasks, and individual observations, thereby facilitating effective execution and cooperation. We validate our approach using the MPE and SMAC benchmarks. Additionally, real-world experiments involving multiple ships demonstrate the effectiveness and practical applicability of the proposed GIPD method.

Deep neural networks are increasingly used for time series tasks, yet they often struggle to interpretably model high-dimensional data. In this context, we consider the task of learning easy to understand connections between time-series variables, and organizing them into subsystems, directly from observed data. Our approach reconstructs multivariate time-series with a masked autoencoder, where all information between individual variables is mediated by a learned adjacency matrix. This intuitive pairwise relationship enables grouping of variables without prior knowledge of cluster quantity or size, and is particularly useful for analyzing complex sensor systems with unknown structural interdependencies. Our method simultaneously learns a useful signal representation and aids in understanding the underlying processes. We show that we can learn the correct subsystems from simulated data, and demonstrate identification of plausible subsystem structure from high-dimensional real-world data. In addition, we show that the model retains high predictive performance.

Automatic landing of tethered unmanned aerial vehicles (UAVs) is an important issue. Typically, UAVs rely on location sensors such as global navigation satellite system (GNSS) and external cameras to obtain location data. However, harsh environments such as denial GNSS or strong winds make it difficult for UAVs to approach the landing area, and common solutions cannot be used for automatic landing. A tethered lifting-wing multicopter has a structure and static stability similar to a kite. Inspired by kites, this paper proposes a new landing method for tethered lifting-wing multicopters, which can be used without location or velocity sensors. During the landing phase, the tethered lifting-wing multicopter only needs to keep the rotor thrust to actively straighten the tethered cable and a constant attitude similar to that of a kite to keep position stability and increase damping. Meanwhile, the winch only needs to recover the cable at a constant speed until the tethered lifting-wing multicopter returns to its base. Real flight experiments demonstrate the feasibility and practicability of this method.

Learned optics, which incorporate lightweight diffractive optics, coded-aperture modulation, and specialized image-processing neural networks, have recently garnered attention in the field of snapshot hyperspectral imaging (HSI). While conventional methods typically rely on a single lens element paired with an off-the-shelf color sensor, these setups, despite their widespread availability, present inherent limitations. First, the Bayer sensor's spectral response curves are not optimized for HSI applications, limiting spectral fidelity of the reconstruction. Second, single lens designs rely on a single diffractive optical element (DOE) to simultaneously encode spectral information and maintain spatial resolution across all wavelengths, which constrains spectral encoding capabilities. This work investigates a multi-channel lens array combined with aperture-wise color filters, all co-optimized alongside an image reconstruction network. This configuration enables independent spatial encoding and spectral response for each channel, improving optical encoding across both spatial and spectral dimensions. Specifically, we validate that the method achieves over a 5dB improvement in PSNR for spectral reconstruction compared to existing single-diffractive lens and coded-aperture techniques. Experimental validation further confirmed that the method is capable of recovering up to 31 spectral bands within the 429--700 nm range in diverse indoor and outdoor environments.

Despite the great interest in the bandit problem, designing efficient algorithms for complex models remains challenging, as there is typically no analytical way to quantify uncertainty. In this paper, we propose Multiplier Bootstrap-based Exploration (MBE), a novel exploration strategy that is applicable to any reward model amenable to weighted loss minimization. We prove both instance-dependent and instance-independent rate-optimal regret bounds for MBE in sub-Gaussian multi-armed bandits. With extensive simulation and real-data experiments, we show the generality and adaptivity of MBE.