The prediction of Remaining Useful Life (RUL) is a critical component in the field of Prognostics and Health Management (PHM), which aims to predict the future state of a system to ensure timely maintenance and prevent unexpected failures (Wang, Xu, Li, Ren, Dong, Chen, Du, Wang, Shi and Zhang, 2024f; Karatzinis, Boutalis and Van Vaerenbergh, 2024; Zhang, Yuan, Jiang and Zhao, 2024b). Accurate RUL prediction enable predictive maintenance, which can significantly reduce downtime, improve safety, and optimize the lifecycle management of machinery and equipment. Additionally, effective RUL prediction can enhance decision-making processes, improve resource allocation, and reduce maintenance costs. In recent years, deep learning has become increasingly important in RUL prediction due to its ability to model complex patterns and dependencies, providing more accurate and reliable predictions compared to traditional methods, such as statistical approaches (Si, Wang, Hu and Zhou, 2011) and physicsbased models (Lei, Li, Gontarz, Lin, Radkowski and Dybala, 2016; Sikorska, Hodkiewicz and Ma, 2011; Li, Zhang, Li and Si, 2024). Existing studies in RUL prediction have primarily focused on utilizing temporal encoders such as Temporal Convolutional Networks (TCN) (Qiu, Niu, Shang, Gao and Xu, 2023), Gated Recurrent Units (GRU), Convolutional Neural Networks (CNN) (Shang, Xu, Qiu, Gao, Jiang and Yi, 2024), and Long Short-Term Memory (LSTM) networks. These methods have achieved strong performance due to their ability to capture temporal information, which refers to the time-based patterns and sequences within the data, such as trends and periodic behaviors. However, they are not effective at capturing spatial information, which limits their performance in RUL prediction.

Automatic text summarization in Nepali language is an unexplored area in natural language processing (NLP). Although considerable research has been dedicated to extractive summarization, the area of abstractive summarization, especially for low-resource languages such as Nepali, remains largely unexplored. This study explores the use of multilingual transformer models, specifically mBART and mT5, for generating headlines for Nepali news articles through abstractive summarization. The research addresses key challenges associated with summarizing texts in Nepali by first creating a summarization dataset through web scraping from various Nepali news portals. These multilingual models were then fine-tuned using different strategies. The performance of the fine-tuned models were then assessed using ROUGE scores and human evaluation to ensure the generated summaries were coherent and conveyed the original meaning. During the human evaluation, the participants were asked to select the best summary among those generated by the models, based on criteria such as relevance, fluency, conciseness, informativeness, factual accuracy, and coverage. During the evaluation with ROUGE scores, the 4-bit quantized mBART with LoRA model was found to be effective in generating better Nepali news headlines in comparison to other models and also it was selected 34.05% of the time during the human evaluation, outperforming all other fine-tuned models created for Nepali News headline generation.

Large Language Models (LLMs) have exhibited exceptional performance across a broad range of tasks and domains. However, they still encounter difficulties in solving mathematical problems due to the rigorous and logical nature of mathematics. Previous studies have employed techniques such as supervised fine-tuning (SFT), prompt engineering, and search-based methods to improve the mathematical problem-solving abilities of LLMs. Despite these efforts, their performance remains suboptimal and demands substantial computational resources. To address this issue, we propose a novel approach, BEATS, to enhance mathematical problem-solving abilities. Our method leverages newly designed prompts that guide the model to iteratively rewrite, advance by one step, and generate answers based on previous steps. Additionally, we employ a pruning tree search to optimize search time while achieving strong performance. Furthermore, we introduce a new back-verification technique that uses LLMs to validate the correctness of the generated answers. Notably, our method improves Qwen2-7b-Instruct's score from 36.94 to 61.52 (outperforming GPT-4's 42.5) on the MATH benchmark.

With this elaborate integration of AI, there is, of course, the fear that AI will take over or replace human talent. However, the recent collaboration between Lionsgate and Runway shows that it has actually been enhancing the process versus diminishing creativity. Instead of replacing their human counterparts, these technologies are being used as tools to help humans cut down on time for specific tasks, which allows them to focus on the joy of creating. It also enables more creative approaches at a lower cost.

Speech signal processing is a cornerstone of modern communication technologies, tasked with improving the clarity and comprehensibility of audio data in noisy environments. The primary challenge in this field is the effective separation and recognition of speech from background noise, crucial for applications ranging from voice-activated assistants to automated transcription services. The quality of speech recognition directly impacts user experience and accessibility in technology-driven communication. This review paper explores advanced clustering techniques, particularly focusing on the Kernel Fuzzy C-Means (KFCM) method, to address these challenges. Our findings indicate that KFCM, compared to traditional methods like K-Means (KM) and Fuzzy C-Means (FCM), provides superior performance in handling non-linear and non-stationary noise conditions in speech signals. The most notable outcome of this review is the adaptability of KFCM to various noisy environments, making it a robust choice for speech enhancement applications. Additionally, the paper identifies gaps in current methodologies, such as the need for more dynamic clustering algorithms that can adapt in real time to changing noise conditions without compromising speech recognition quality. Key contributions include a detailed comparative analysis of current clustering algorithms and suggestions for further integrating hybrid models that combine KFCM with neural networks to enhance speech recognition accuracy. Through this review, we advocate for a shift towards more sophisticated, adaptive clustering techniques that can significantly improve speech enhancement and pave the way for more resilient speech processing systems.

Urban Building Exteriors are increasingly important in urban analytics, driven by advancements in Street View Imagery and its integration with urban research. Multimodal Large Language Models (LLMs) offer powerful tools for urban annotation, enabling deeper insights into urban environments. However, challenges remain in creating accurate and detailed urban building exterior databases, identifying critical indicators for energy efficiency, environmental sustainability, and human-centric design, and systematically organizing these indicators. To address these challenges, we propose BuildingView, a novel approach that integrates high-resolution visual data from Google Street View with spatial information from OpenStreetMap via the Overpass API. This research improves the accuracy of urban building exterior data, identifies key sustainability and design indicators, and develops a framework for their extraction and categorization. Our methodology includes a systematic literature review, building and Street View sampling, and annotation using the ChatGPT-4O API. The resulting database, validated with data from New York City, Amsterdam, and Singapore, provides a comprehensive tool for urban studies, supporting informed decision-making in urban planning, architectural design, and environmental policy. The code for BuildingView is available at https://github.com/Jasper0122/BuildingView.

In warehouse environments, robots require robust picking capabilities to manage a wide variety of objects. Effective deployment demands minimal hardware, strong generalization to new products, and resilience in diverse settings. Current methods often rely on depth sensors for structural information, which suffer from high costs, complex setups, and technical limitations. Inspired by recent advancements in computer vision, we propose an innovative approach that leverages foundation models to enhance suction grasping using only RGB images. Trained solely on a synthetic dataset, our method generalizes its grasp prediction capabilities to real-world robots and a diverse range of novel objects not included in the training set. Our network achieves an 82.3\% success rate in real-world applications. The project website with code and data will be available at http://optigrasp.github.io.

Deep Multi-agent Reinforcement Learning (MARL) relies on neural networks with numerous parameters in multi-agent scenarios, often incurring substantial computational overhead. Consequently, there is an urgent need to expedite training and enable model compression in MARL. This paper proposes the utilization of dynamic sparse training (DST), a technique proven effective in deep supervised learning tasks, to alleviate the computational burdens in MARL training. However, a direct adoption of DST fails to yield satisfactory MARL agents, leading to breakdowns in value learning within deep sparse value-based MARL models. Motivated by this challenge, we introduce an innovative Multi-Agent Sparse Training (MAST) framework aimed at simultaneously enhancing the reliability of learning targets and the rationality of sample distribution to improve value learning in sparse models. Specifically, MAST incorporates the Soft Mellowmax Operator with a hybrid TD-($\lambda$) schema to establish dependable learning targets. Additionally, it employs a dual replay buffer mechanism to enhance the distribution of training samples. Building upon these aspects, MAST utilizes gradient-based topology evolution to exclusively train multiple MARL agents using sparse networks. Our comprehensive experimental investigation across various value-based MARL algorithms on multiple benchmarks demonstrates, for the first time, significant reductions in redundancy of up to $20\times$ in Floating Point Operations (FLOPs) for both training and inference, with less than $3\%$ performance degradation.

The rapid scaling of AI has spurred a growing emphasis on ethical considerations in both development and practice. This has led to the formulation of increasingly sophisticated model auditing and reporting requirements, as well as governance frameworks to mitigate potential risks to individuals and society. At this critical juncture, we review the practical challenges of promoting responsible AI and transparency in informal sectors like OSS that support vital infrastructure and see widespread use. We focus on how model performance evaluation may inform or inhibit probing of model limitations, biases, and other risks. Our controlled analysis of 7903 Hugging Face projects found that risk documentation is strongly associated with evaluation practices. Yet, submissions (N=789) from the platform's most popular competitive leaderboard showed less accountability among high performers. Our findings can inform AI providers and legal scholars in designing interventions and policies that preserve open-source innovation while incentivizing ethical uptake.

Goal-directed interactive agents, which autonomously complete tasks through interactions with their environment, can assist humans in various domains of their daily lives. Recent advances in large language models (LLMs) led to a surge of new, more and more challenging tasks to evaluate such agents. To properly contextualize performance across these tasks, it is imperative to understand the different challenges they pose to agents. To this end, this survey compiles relevant tasks and environments for evaluating goal-directed interactive agents, structuring them along dimensions relevant for understanding current obstacles. An up-to-date compilation of relevant resources can be found on our project website: https://coli-saar.github.io/interactive-agents.