Abstract--Despite recent progress in trajectory planning for multiple robots and a single tethered robot, trajectory planning for multiple tethered robots to reach their individual targets without entanglements remains a challenging problem. In this paper, a complete approach is presented to address this problem. First, a multi-robot tether-aware representation of homotopy is proposed to efficiently evaluate the feasibility and safety of a potential path in terms of (1) the cable length required to reach a target following the path, and (2) the risk of entanglements with the cables of other robots. Top-down view of a workspace to illustrate an entanglement situation. The efficiency of the proposed homotopy representation is compared against the existing single and multiple tethered robot planning approaches. While there exists abundant literature on multi-robot path I. NMANNED vehicles such as unmanned aerial vehicles (UAVs), unmanned ground vehicles (UGVs) and unmanned robot planning problem focus on the single robot case and surface vehicles (USVs) have been widely adopted use a representation of homotopy to identify the path or cable in industrial applications due to reduced safety hazards for configuration [8]-[11]. Feasible paths are found by searching humans and potential cost saving [1], [2]. For autonomous tethered robots, it is robots efficiently. Moreover, slow graph expansion requires important to consider the risk of the tether being entangled offline construction of the graph prior to online planning. Each robot is attached to one end of a slack and online trajectory generation framework for non-entangling flexible cable that is allowed to lie on the ground.

Deep neural networks (DNNs) have promoted the development of computer aided diagnosis (CAD) systems for fundus diseases, helping ophthalmologists reduce missed diagnosis and misdiagnosis rate. However, the majority of CAD systems are data-driven but lack of medical prior knowledge which can be performance-friendly. In this regard, we innovatively proposed a human-in-the-loop (HITL) CAD system by leveraging ophthalmologists' eye-tracking information, which is more efficient and accurate. Concretely, the HITL CAD system was implemented on the multiple instance learning (MIL), where eye-tracking gaze maps were beneficial to cherry-pick diagnosis-related instances. Furthermore, the dual-cross-attention MIL (DCAMIL) network was utilized to curb the adverse effects of noisy instances. Meanwhile, both sequence augmentation module and domain adversarial module were introduced to enrich and standardize instances in the training bag, respectively, thereby enhancing the robustness of our method. We conduct comparative experiments on our newly constructed datasets (namely, AMD-Gaze and DR-Gaze), respectively for the AMD and early DR detection. Rigorous experiments demonstrate the feasibility of our HITL CAD system and the superiority of the proposed DCAMIL, fully exploring the ophthalmologists' eye-tracking information. These investigations indicate that physicians' gaze maps, as medical prior knowledge, is potential to contribute to the CAD systems of clinical diseases.

However, While VAEs are nowadays omnipresent in the field of machine in practice, they suffer from a problem called learning, it is also widely recognized that there remain posterior collapse, which occurs when the encoder in practice some major challenges that still require effective coincides, or collapses, with the prior taking no solutions. Notably, they suffer from the problem of information from the latent structure of the input posterior collapse, which occurs when the distribution corresponding data into consideration. In this work, we introduce to the encoder coincides, or collapses, with the an inverse Lipschitz neural network into the prior taking no information from the latent structure of the decoder and, based on this architecture, provide a input data into consideration. Also known as KL vanishing new method that can control in a simple and clear or over-pruning, this phenomenon makes VAEs incapable manner the degree of posterior collapse for a wide to produce pertinent representations and has been reportedly range of VAE models equipped with a concrete observed in many fields (e.g., Bowman et al. (2016); Fu et al. theoretical guarantee. We also illustrate the effectiveness (2019); Wang & Ziyin (2022); Yeung et al. (2017)). There of our method through several numerical exists now a large body of literature that examines its underlying experiments.

We describe our contribution to the SemEVAl 2023 AfriSenti-SemEval shared task, where we tackle the task of sentiment analysis in 14 different African languages. We develop both monolingual and multilingual models under a full supervised setting (subtasks A and B). We also develop models for the zero-shot setting (subtask C). Our approach involves experimenting with transfer learning using six language models, including further pertaining of some of these models as well as a final finetuning stage. Our best performing models achieve an F1-score of 70.36 on development data and an F1-score of 66.13 on test data. Unsurprisingly, our results demonstrate the effectiveness of transfer learning and fine-tuning techniques for sentiment analysis across multiple languages. Our approach can be applied to other sentiment analysis tasks in different languages and domains.

Capsule Networks (CapsNets) are able to hierarchically preserve the pose relationships between multiple objects for image classification tasks. Other than achieving high accuracy, another relevant factor in deploying CapsNets in safety-critical applications is the robustness against input transformations and malicious adversarial attacks. In this paper, we systematically analyze and evaluate different factors affecting the robustness of CapsNets, compared to traditional Convolutional Neural Networks (CNNs). Towards a comprehensive comparison, we test two CapsNet models and two CNN models on the MNIST, GTSRB, and CIFAR10 datasets, as well as on the affine-transformed versions of such datasets. With a thorough analysis, we show which properties of these architectures better contribute to increasing the robustness and their limitations. Overall, CapsNets achieve better robustness against adversarial examples and affine transformations, compared to a traditional CNN with a similar number of parameters. Similar conclusions have been derived for deeper versions of CapsNets and CNNs. Moreover, our results unleash a key finding that the dynamic routing does not contribute much to improving the CapsNets' robustness. Indeed, the main generalization contribution is due to the hierarchical feature learning through capsules.

A system that could reliably identify and sum up the most important points of a conversation would be valuable in a wide variety of real-world contexts, from business meetings to medical consultations to customer service calls. Recent advances in deep learning, and especially the invention of encoder-decoder architectures, has significantly improved language generation systems, opening the door to improved forms of abstractive summarization, a form of summarization particularly well-suited for multi-party conversation. In this paper, we provide an overview of the challenges raised by the task of abstractive meeting summarization and of the data sets, models and evaluation metrics that have been used to tackle the problems.

It is well-known that document context is vital for resolving a range of translation ambiguities, and in fact the document setting is the most natural setting for nearly all translation. It is therefore unfortunate that machine translation -- both research and production -- largely remains stuck in a decades-old sentence-level translation paradigm. It is also an increasingly glaring problem in light of competitive pressure from large language models, which are natively document-based. Much work in document-context machine translation exists, but for various reasons has been unable to catch hold. This paper suggests a path out of this rut by addressing three impediments at once: what architectures should we use? where do we get document-level information for training them? and how do we know whether they are any good? In contrast to work on specialized architectures, we show that the standard Transformer architecture is sufficient, provided it has enough capacity. Next, we address the training data issue by taking document samples from back-translated data only, where the data is not only more readily available, but is also of higher quality compared to parallel document data, which may contain machine translation output. Finally, we propose generative variants of existing contrastive metrics that are better able to discriminate among document systems. Results in four large-data language pairs (DE$\rightarrow$EN, EN$\rightarrow$DE, EN$\rightarrow$FR, and EN$\rightarrow$RU) establish the success of these three pieces together in improving document-level performance.

Although media bias detection is a complex multi-task problem, there is, to date, no unified benchmark grouping these evaluation tasks. We introduce the Media Bias Identification Benchmark (MBIB), a comprehensive benchmark that groups different types of media bias (e.g., linguistic, cognitive, political) under a common framework to test how prospective detection techniques generalize. After reviewing 115 datasets, we select nine tasks and carefully propose 22 associated datasets for evaluating media bias detection techniques. We evaluate MBIB using state-of-the-art Transformer techniques (e.g., T5, BART). Our results suggest that while hate speech, racial bias, and gender bias are easier to detect, models struggle to handle certain bias types, e.g., cognitive and political bias. However, our results show that no single technique can outperform all the others significantly. We also find an uneven distribution of research interest and resource allocation to the individual tasks in media bias. A unified benchmark encourages the development of more robust systems and shifts the current paradigm in media bias detection evaluation towards solutions that tackle not one but multiple media bias types simultaneously.

The paper considers the DIverse MultiPLEx (DIMPLE) network model, introduced in Pensky and Wang (2021), where all layers of the network have the same collection of nodes and are equipped with the Stochastic Block Models. In addition, all layers can be partitioned into groups with the same community structures, although the layers in the same group may have different matrices of block connection probabilities. The DIMPLE model generalizes a multitude of papers that study multilayer networks with the same community structures in all layers, as well as the Mixture Multilayer Stochastic Block Model (MMLSBM), where the layers in the same group have identical matrices of block connection probabilities. While Pensky and Wang (2021) applied spectral clustering to the proxy of the adjacency tensor, the present paper uses Sparse Subspace Clustering (SSC) for identifying groups of layers with identical community structures. Under mild conditions, the latter leads to the strongly consistent between-layer clustering. In addition, SSC allows to handle much larger networks than methodology of Pensky and Wang (2021), and is perfectly suitable for application of parallel computing.

Subword tokenization has been widely successful in text-based natural language processing (NLP) tasks with Transformer-based models. As Transformer models become increasingly popular in symbolic music-related studies, it is imperative to investigate the efficacy of subword tokenization in the symbolic music domain. In this paper, we explore subword tokenization techniques, such as byte-pair encoding (BPE), in symbolic music generation and its impact on the overall structure of generated songs. Our experiments are based on three types of MIDI datasets: single track-melody only, multi-track with a single instrument, and multi-track and multi-instrument. We apply subword tokenization on post-musical tokenization schemes and find that it enables the generation of longer songs at the same time and improves the overall structure of the generated music in terms of objective metrics like structure indicator (SI), Pitch Class Entropy, etc. We also compare two subword tokenization methods, BPE and Unigram, and observe that both methods lead to consistent improvements. Our study suggests that subword tokenization is a promising technique for symbolic music generation and may have broader implications for music composition, particularly in cases involving complex data such as multi-track songs.