With the promise of greater safety and adaptability, modular reconfigurable uncrewed air vehicles have been proposed as unique, versatile platforms holding the potential to replace multiple types of monolithic vehicles at once. State-of-the-art rigidly assembled modular vehicles are generally two-dimensional configurations in which the rotors are coplanar and assume the shape of a "flight array". We introduce the Dodecacopter, a new type of modular rotorcraft where all modules take the shape of a regular dodecahedron, allowing the creation of richer sets of configurations beyond flight arrays. In particular, we show how the chosen module design can be used to create three-dimensional and fully actuated configurations. We justify the relevance of these types of configurations in terms of their structural and actuation properties with various performance indicators. Given the broad range of configurations and capabilities that can be achieved with our proposed design, we formulate tractable optimization programs to find optimal configurations given structural and actuation constraints. Finally, a prototype of such a vehicle is presented along with results of performed flights in multiple configurations.

With the increasing availability of Foundation Models, federated tuning has garnered attention in the field of federated learning, utilizing data and computation resources from multiple clients to collaboratively fine-tune foundation models. However, in real-world federated scenarios, there often exist a multitude of heterogeneous clients with varying computation and communication resources, rendering them incapable of supporting the entire model fine-tuning process. In response to this challenge, we propose a novel federated tuning algorithm, FedRA. The implementation of FedRA is straightforward and can be seamlessly integrated into any transformer-based model without the need for further modification to the original model. Specifically, in each communication round, FedRA randomly generates an allocation matrix. For resource-constrained clients, it reorganizes a small number of layers from the original model based on the allocation matrix and fine-tunes using LoRA. Subsequently, the server aggregates the updated LoRA parameters from the clients according to the current allocation matrix into the corresponding layers of the original model. It is worth noting that FedRA also supports scenarios where none of the clients can support the entire global model, which is an impressive advantage. We conduct experiments on two large-scale image datasets, DomainNet and NICO++, under various non-iid settings. The results demonstrate that FedRA outperforms the compared methods significantly. The source code is available at \url{https://github.com/leondada/FedRA}.

This paper presents a theoretical study on the ability of multi-rotor aerial vehicles (MRAVs) with tiltable propellers to achieve and sustain static hovering at different orientations. To analyze the ability of MRAVs with tiltable propellers to achieve static hovering, a novel linear map between the platform's control inputs and applied forces and moments is introduced. The relation between the introduced map and the platform's ability to hover at different orientations is developed. Correspondingly, the conditions for MRAVs with tiltable propellers to realize and sustain static hovering are detailed. A numerical metric is then introduced, which reflects the ability of MRAVs to sustain static hovering at different orientations. A subclass of MRAVs with tiltable propellers is defined as the Critically Statically Hoverable platforms (CSH), where CSH platforms are MRAVs that cannot sustain static hovering with fixed propellers, but can achieve static hovering with tilting propellers. Finally, extensive simulations are conducted to test and validate the above findings, and to demonstrate the effect of the proposed numerical metric on the platform's dynamics.

Ensembles of Deep Neural Networks (DNNs) have achieved qualitative predictions but they are computing and memory intensive. Therefore, the demand is growing to make them answer a heavy workload of requests with available computational resources. Unlike recent initiatives on inference servers and inference frameworks, which focus on the prediction of single DNNs, we propose a new software layer to serve with flexibility and efficiency ensembles of DNNs. Our inference system is designed with several technical innovations. First, we propose a novel procedure to find a good allocation matrix between devices (CPUs or GPUs) and DNN instances. It runs successively a worst-fit to allocate DNNs into the memory devices and a greedy algorithm to optimize allocation settings and speed up the ensemble. Second, we design the inference system based on multiple processes to run asynchronously: batching, prediction, and the combination rule with an efficient internal communication scheme to avoid overhead. Experiments show the flexibility and efficiency under extreme scenarios: It successes to serve an ensemble of 12 heavy DNNs into 4 GPUs and at the opposite, one single DNN multi-threaded into 16 GPUs. It also outperforms the simple baseline consisting of optimizing the batch size of DNNs by a speedup up to 2.7X on the image classification task.

Over the last fifty years, a large body of research in microeconomics has introduced many different mechanisms for resource allocation. Despite the wide variety of available options, "simple" mechanisms such as posted price and serial dictatorship are often preferred for practical applications, including housing allocation [Abdulkadiroğlu and Sönmez, 1998], online procurement [Badanidiyuru et al., 2012], or allocation of medical appointments [Klaus and Nichifor, 2019]. There has been considerable interest in formalizing different notions of simplicity. Li [2017] identifies mechanisms that are particularly simple from a strategic perspective, introducing the concept of obviously strategyproof mechanisms; under obviously strategyproof mechanisms, it is obvious that an agent cannot profit by trying to game the system, as even the worst possible final outcome from behaving truthfully is at least as good as the best possible outcome from any other strategy. Pycia and Troyan [2019] introduce the still stronger concept of strongly obviously strategyproof (SOSP) mechanisms, and show that this class can essentially be identified with sequential price mechanisms, where agents are visited in turn and offered a choice from a menu of options (which may or may not include transfers). SOSP mechanisms are ones in which an agent is not even required to consider her future (truthful) actions to understand that the mechanism is obviously strategyproof.

We present the Wright-Fisher Indian buffet process (WF-IBP), a probabilistic model for time-dependent data assumed to have been generated by an unknown number of latent features. This model is suitable as a prior in Bayesian nonparametric feature allocation models in which the features underlying the observed data exhibit a dependency structure over time. More specifically, we establish a new framework for generating dependent Indian buffet processes, where the Poisson random field model from population genetics is used as a way of constructing dependent beta processes. Inference in the model is complex, and we describe a sophisticated Markov Chain Monte Carlo algorithm for exact posterior simulation. We apply our construction to develop a nonparametric focused topic model for collections of time-stamped text documents and test it on the full corpus of NIPS papers published from 1987 to 2015.