We propose a method for providing communication network infrastructure in autonomous multi-agent teams. In particular, we consider a set of communication agents that are placed alongside regular agents from the system in order to improve the rate of information transfer between the latter. In order to find the optimal positions to place such agents, we define a flexible performance function that adapts to network requirements for different systems. We provide an algorithm based on shadow prices of a related convex optimization problem in order to drive the configuration of the complete system towards a local maximum. We apply our method to three different performance functions associated with three practical scenarios in which we show both the performance of the algorithm and the flexibility it allows for optimizing different network requirements.

Deployment in hazardous environments requires robots to understand the risks associated with their actions and movements to prevent accidents. Despite its importance, these risks are not explicitly modeled by currently deployed locomotion controllers for legged robots. In this work, we propose a risk sensitive locomotion training method employing distributional reinforcement learning to consider safety explicitly. Instead of relying on a value expectation, we estimate the complete value distribution to account for uncertainty in the robot's interaction with the environment. The value distribution is consumed by a risk metric to extract risk sensitive value estimates. These are integrated into Proximal Policy Optimization (PPO) to derive our method, Distributional Proximal Policy Optimization (DPPO). The risk preference, ranging from risk-averse to risk-seeking, can be controlled by a single parameter, which enables to adjust the robot's behavior dynamically. Importantly, our approach removes the need for additional reward function tuning to achieve risk sensitivity. We show emergent risk sensitive locomotion behavior in simulation and on the quadrupedal robot ANYmal.

Document-level Neural Machine Translation (DocNMT) has been proven crucial for handling discourse phenomena by introducing document-level context information. One of the most important directions is to input the whole document directly to the standard Transformer model. In this case, efficiency becomes a critical concern due to the quadratic complexity of the attention module. Existing studies either focus on the encoder part, which cannot be deployed on sequence-to-sequence generation tasks, e.g., Machine Translation (MT), or suffer from a significant performance drop. In this work, we keep the translation performance while gaining 20\% speed up by introducing extra selection layer based on lightweight attention that selects a small portion of tokens to be attended. It takes advantage of the original attention to ensure performance and dimension reduction to accelerate inference. Experimental results show that our method could achieve up to 95\% sparsity (only 5\% tokens attended) approximately, and save 93\% computation cost on the attention module compared with the original Transformer, while maintaining the performance.

The advent of serverless computing has ushered in notable advancements in distributed machine learning, particularly within parameter server-based architectures. Yet, the integration of serverless features within peer-to-peer (P2P) distributed networks remains largely uncharted. In this paper, we introduce SPIRT, a fault-tolerant, reliable, and secure serverless P2P ML training architecture. designed to bridge this existing gap. Capitalizing on the inherent robustness and reliability innate to P2P systems, SPIRT employs RedisAI for in-database operations, leading to an 82\% reduction in the time required for model updates and gradient averaging across a variety of models and batch sizes. This architecture showcases resilience against peer failures and adeptly manages the integration of new peers, thereby highlighting its fault-tolerant characteristics and scalability. Furthermore, SPIRT ensures secure communication between peers, enhancing the reliability of distributed machine learning tasks. Even in the face of Byzantine attacks, the system's robust aggregation algorithms maintain high levels of accuracy. These findings illuminate the promising potential of serverless architectures in P2P distributed machine learning, offering a significant stride towards the development of more efficient, scalable, and resilient applications.

Previous work identified temporal bias in an Italian hate In recent years, researchers have developed a huge variety speech data set associated with immigrants (Florio et al. of machine learning models that can automatically detect 2020). However, they have yet to explore temporal factors abusive language (Mishra et al. 2019; Aurpa, Sadik, and affecting predictive performance from a multilingual perspective. Ahmed 2022; Das and Mukherjee 2023; Alrashidi, Jamal, In this paper, we explore temporal bias in 5 different and Alkhathlan 2023). However, these models may be subject abusive data sets that span varying time periods, in 4 to temporal bias, which can lead to a decrease in the languages (English, Spanish, Italian, and Chinese). Specifically, accuracy of abusive language detection models, potentially we investigate the following core research questions: allowing abusive language to be undetected or falsely detected. RQ1: How does the magnitude of temporal bias vary across different data sets such as language, time span and Temporal bias arises from differences in populations and collection methods?

The increasing demand for computational power in big data and machine learning has driven the development of distributed training methodologies. Among these, peer-to-peer (P2P) networks provide advantages such as enhanced scalability and fault tolerance. However, they also encounter challenges related to resource consumption, costs, and communication overhead as the number of participating peers grows. In this paper, we introduce a novel architecture that combines serverless computing with P2P networks for distributed training and present a method for efficient parallel gradient computation under resource constraints. Our findings show a significant enhancement in gradient computation time, with up to a 97.34\% improvement compared to conventional P2P distributed training methods. As for costs, our examination confirmed that the serverless architecture could incur higher expenses, reaching up to 5.4 times more than instance-based architectures. It is essential to consider that these higher costs are associated with marked improvements in computation time, particularly under resource-constrained scenarios. Despite the cost-time trade-off, the serverless approach still holds promise due to its pay-as-you-go model. Utilizing dynamic resource allocation, it enables faster training times and optimized resource utilization, making it a promising candidate for a wide range of machine learning applications.

Internal language model (ILM) subtraction has been widely applied to improve the performance of the RNN-Transducer with external language model (LM) fusion for speech recognition. In this work, we show that sequence discriminative training has a strong correlation with ILM subtraction from both theoretical and empirical points of view. Theoretically, we derive that the global optimum of maximum mutual information (MMI) training shares a similar formula as ILM subtraction. Empirically, we show that ILM subtraction and sequence discriminative training achieve similar performance across a wide range of experiments on Librispeech, including both MMI and minimum Bayes risk (MBR) criteria, as well as neural transducers and LMs of both full and limited context. The benefit of ILM subtraction also becomes much smaller after sequence discriminative training. We also provide an in-depth study to show that sequence discriminative training has a minimal effect on the commonly used zero-encoder ILM estimation, but a joint effect on both encoder and prediction + joint network for posterior probability reshaping including both ILM and blank suppression.

Modeling long-term context in videos is crucial for many fine-grained tasks including temporal action segmentation. An interesting question that is still open is how much long-term temporal context is needed for optimal performance. While transformers can model the long-term context of a video, this becomes computationally prohibitive for long videos. Recent works on temporal action segmentation thus combine temporal convolutional networks with self-attentions that are computed only for a local temporal window. While these approaches show good results, their performance is limited by their inability to capture the full context of a video. In this work, we try to answer how much long-term temporal context is required for temporal action segmentation by introducing a transformer-based model that leverages sparse attention to capture the full context of a video. We compare our model with the current state of the art on three datasets for temporal action segmentation, namely 50Salads, Breakfast, and Assembly101. Our experiments show that modeling the full context of a video is necessary to obtain the best performance for temporal action segmentation.

Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence, especially when tackling complex tasks. While the chain-of-thought (CoT) technique has gained considerable attention, the existing ScienceQA dataset, which focuses on multimodal scientific questions and explanations from elementary and high school textbooks, lacks a comprehensive evaluation of diverse approaches. To address this gap, we present COCO Multi-Modal Reasoning(COCO-MMR) dataset, a novel dataset that encompasses an extensive collection of open-ended questions, rationales, and answers derived from the large object dataset COCO. Unlike previous datasets that rely on multiple-choice questions, our dataset pioneers the use of open-ended questions in the context of multimodal CoT, introducing a more challenging problem that effectively assesses the reasoning capability of CoT models. Through comprehensive evaluations and detailed analyses, we provide valuable insights and propose innovative techniques, including multi-hop cross-modal attention and sentence-level contrastive learning, to enhance the image and text encoders. Extensive experiments demonstrate the efficacy of the proposed dataset and techniques, offering novel perspectives for advancing multimodal reasoning. The data and code are available at \href{https://github.com/weijingxuan/COCO-MMR}{https://github.com/weijingxuan/COCO-MMR}.

We introduce Text2Cinemagraph, a fully automated method for creating cinemagraphs from text descriptions - an especially challenging task when prompts feature imaginary elements and artistic styles, given the complexity of interpreting the semantics and motions of these images. We focus on cinemagraphs of fluid elements, such as flowing rivers, and drifting clouds, which exhibit continuous motion and repetitive textures. Existing single-image animation methods fall short on artistic inputs, and recent text-based video methods frequently introduce temporal inconsistencies, struggling to keep certain regions static. To address these challenges, we propose an idea of synthesizing image twins from a single text prompt - a pair of an artistic image and its pixel-aligned corresponding natural-looking twin. While the artistic image depicts the style and appearance detailed in our text prompt, the realistic counterpart greatly simplifies layout and motion analysis. Leveraging existing natural image and video datasets, we can accurately segment the realistic image and predict plausible motion given the semantic information. The predicted motion can then be transferred to the artistic image to create the final cinemagraph. Our method outperforms existing approaches in creating cinemagraphs for natural landscapes as well as artistic and other-worldly scenes, as validated by automated metrics and user studies. Finally, we demonstrate two extensions: animating existing paintings and controlling motion directions using text.