The increasing complexity of Industry 4.0 systems brings new challenges regarding predictive maintenance tasks such as fault detection and diagnosis. A corresponding and realistic setting includes multi-source data streams from different modalities, such as sensors measurements time series, machine images, textual maintenance reports, etc. These heterogeneous multimodal streams also differ in their acquisition frequency, may embed temporally unaligned information and can be arbitrarily long, depending on the considered system and task. Whereas multimodal fusion has been largely studied in a static setting, to the best of our knowledge, there exists no previous work considering arbitrarily long multimodal streams alongside with related tasks such as prediction across time. Thus, in this paper, we first formalize this paradigm of heterogeneous multimodal learning in a streaming setting as a new one. To tackle this challenge, we propose StreaMulT, a Streaming Multimodal Transformer relying on cross-modal attention and on a memory bank to process arbitrarily long input sequences at training time and run in a streaming way at inference. StreaMulT improves the state-of-the-art metrics on CMU-MOSEI dataset for Multimodal Sentiment Analysis task, while being able to deal with much longer inputs than other multimodal models. The conducted experiments eventually highlight the importance of the textual embedding layer, questioning recent improvements in Multimodal Sentiment Analysis benchmarks.

Many deep learning synthetic speech generation tools are readily available. The use of synthetic speech has caused financial fraud, impersonation of people, and misinformation to spread. For this reason forensic methods that can detect synthetic speech have been proposed. Existing methods often overfit on one dataset and their performance reduces substantially in practical scenarios such as detecting synthetic speech shared on social platforms. In this paper we propose, Patched Spectrogram Synthetic Speech Detection Transformer (PS3DT), a synthetic speech detector that converts a time domain speech signal to a mel-spectrogram and processes it in patches using a transformer neural network. We evaluate the detection performance of PS3DT on ASVspoof2019 dataset. Our experiments show that PS3DT performs well on ASVspoof2019 dataset compared to other approaches using spectrogram for synthetic speech detection. We also investigate generalization performance of PS3DT on In-the-Wild dataset. PS3DT generalizes well than several existing methods on detecting synthetic speech from an out-of-distribution dataset. We also evaluate robustness of PS3DT to detect telephone quality synthetic speech and synthetic speech shared on social platforms (compressed speech). PS3DT is robust to compression and can detect telephone quality synthetic speech better than several existing methods.

Advancements in technology are steering attention toward creating comfortable and acceptable driving characteristics in autonomous vehicles. Ensuring a safe and comfortable ride experience is vital for the widespread adoption of autonomous vehicles, as mismatches in driving styles between humans and autonomous systems can impact passenger confidence. Current driving functions have fixed parameters, and there is no universally agreed-upon driving style for autonomous vehicles. Integrating driving style preferences into automated vehicles may enhance acceptance and reduce uncertainty, expediting their adoption. A controlled vehicle study (N = 62) was conducted with a variety of German participants to identify the individual lateral driving behavior of human drivers, specifically emphasizing rural roads. We introduce novel indicators for assessing stationary and transient curve negotiation, directly applicable in developing personalized lateral driving functions. To assess the predictability of these indicators using self-reports, we introduce the MDSI-DE, the German version of the Multidimensional Driving Style Inventory. The correlation analysis between MDSI factor scores and proposed indicators showed modest but significant associations, primarily with acceleration and jerk statistics while the in-depth lateral driving behavior turned out to be highly driver-heterogeneous. The dataset including the anonymized socio-demographics and questionnaire responses, the raw vehicle measurements including labels, and the derived driving behavior indicators are publicly available at https://www.kaggle.com/datasets/jhaselberger/spodb-subject-study-of-lateral-vehicle-guidance.

The transit method allows the detection and characterization of planetary systems by analyzing stellar light curves. Convolutional neural networks appear to offer a viable solution for automating these analyses. In this research, two 1D convolutional neural network models, which work with simulated light curves in which transit-like signals were injected, are presented. One model operates on complete light curves and estimates the orbital period, and the other one operates on phase-folded light curves and estimates the semimajor axis of the orbit and the square of the planet-to-star radius ratio. Both models were tested on real data from TESS light curves with confirmed planets to ensure that they are able to work with real data. The results obtained show that 1D CNNs are able to characterize transiting exoplanets from their host star's detrended light curve and, furthermore, reducing both the required time and computational costs compared with the current detection and characterization algorithms.

The adoption of machine learning (ML) and, more specifically, deep learning (DL) applications into all major areas of our lives is underway. The development of trustworthy AI is especially important in medicine due to the large implications for patients' lives. While trustworthiness concerns various aspects including ethical, technical and privacy requirements, we focus on the importance of data quality (training/test) in DL. Since data quality dictates the behaviour of ML products, evaluating data quality will play a key part in the regulatory approval of medical AI products. We perform a systematic review following PRISMA guidelines using the databases PubMed and ACM Digital Library. We identify 2362 studies, out of which 62 records fulfil our eligibility criteria. From this literature, we synthesise the existing knowledge on data quality frameworks and combine it with the perspective of ML applications in medicine. As a result, we propose the METRIC-framework, a specialised data quality framework for medical training data comprising 15 awareness dimensions, along which developers of medical ML applications should investigate a dataset. This knowledge helps to reduce biases as a major source of unfairness, increase robustness, facilitate interpretability and thus lays the foundation for trustworthy AI in medicine. Incorporating such systematic assessment of medical datasets into regulatory approval processes has the potential to accelerate the approval of ML products and builds the basis for new standards.

Taxonomies represent an arborescence hierarchical structure that establishes relationships among entities to convey knowledge within a specific domain. Each edge in the taxonomy signifies a hypernym-hyponym relationship. Taxonomies find utility in various real-world applications, such as e-commerce search engines and recommendation systems. Consequently, there arises a necessity to enhance these taxonomies over time. However, manually curating taxonomies with neoteric data presents challenges due to limitations in available human resources and the exponential growth of data. Therefore, it becomes imperative to develop automatic taxonomy expansion methods. Traditional supervised taxonomy expansion approaches encounter difficulties stemming from limited resources, primarily due to the small size of existing taxonomies. This scarcity of training data often leads to overfitting. In this paper, we propose FLAME, a novel approach for taxonomy expansion in low-resource environments by harnessing the capabilities of large language models that are trained on extensive real-world knowledge. LLMs help compensate for the scarcity of domain-specific knowledge. Specifically, FLAME leverages prompting in few-shot settings to extract the inherent knowledge within the LLMs, ascertaining the hypernym entities within the taxonomy. Furthermore, it employs reinforcement learning to fine-tune the large language models, resulting in more accurate predictions. Experiments on three real-world benchmark datasets demonstrate the effectiveness of FLAME in real-world scenarios, achieving a remarkable improvement of 18.5% in accuracy and 12.3% in Wu & Palmer metric over eight baselines. Furthermore, we elucidate the strengths and weaknesses of FLAME through an extensive case study, error analysis and ablation studies on the benchmarks.

Large Language Models with transformer architecture have revolutionized the domain of text generation, setting unprecedented benchmarks. Despite their impressive capabilities, LLMs have been criticized for generating outcomes that deviate from factual accuracy or display logical inconsistencies, phenomena commonly referred to as hallucinations. This term, however, has often been misapplied to any results deviating from the instructor's expectations, which this paper defines as attention misdirection rather than true hallucinations. Understanding the distinction between hallucinations and attention misdirection becomes increasingly relevant in business contexts, where the ramifications of such errors can significantly impact the value extraction from these inherently pre-trained models. This paper highlights the best practices of the PGI, Persona, Grouping, and Intelligence, method, a strategic framework that achieved a remarkable error rate of only 3,15 percent across 4,000 responses generated by GPT in response to a real business challenge. It emphasizes that by equipping experimentation with knowledge, businesses can unlock opportunities for innovation through the use of these natively pre-trained models. This reinforces the notion that strategic application grounded in a skilled team can maximize the benefits of emergent technologies such as the LLMs.

Long video understanding is a significant and ongoing challenge in the intersection of multimedia and artificial intelligence. Employing large language models (LLMs) for comprehending video becomes an emerging and promising method. However, this approach incurs high computational costs due to the extensive array of video tokens, experiences reduced visual clarity as a consequence of token aggregation, and confronts challenges arising from irrelevant visual tokens while answering video-related questions. To alleviate these issues, we present an Interactive Visual Adapter (IVA) within LLMs, designed to enhance interaction with fine-grained visual elements. Specifically, we first transform long videos into temporal video tokens via leveraging a visual encoder alongside a pretrained causal transformer, then feed them into LLMs with the video instructions. Subsequently, we integrated IVA, which contains a lightweight temporal frame selector and a spatial feature interactor, within the internal blocks of LLMs to capture instruction-aware and fine-grained visual signals. Consequently, the proposed video-LLM facilitates a comprehensive understanding of long video content through appropriate long video modeling and precise visual interactions. We conducted extensive experiments on nine video understanding benchmarks and experimental results show that our interactive visual adapter significantly improves the performance of video LLMs on long video QA tasks. Ablation studies further verify the effectiveness of IVA in long and short video understandings.

Social media platforms are hubs for multimodal information exchange, encompassing text, images, and videos, making it challenging for machines to comprehend the information or emotions associated with interactions in online spaces. Multimodal Large Language Models (MLLMs) have emerged as a promising solution to address these challenges, yet struggle with accurately interpreting human emotions and complex contents like misinformation. This paper introduces MM-Soc, a comprehensive benchmark designed to evaluate MLLMs' understanding of multimodal social media content. MM-Soc compiles prominent multimodal datasets and incorporates a novel large-scale YouTube tagging dataset, targeting a range of tasks from misinformation detection, hate speech detection, and social context generation. Through our exhaustive evaluation on ten size-variants of four open-source MLLMs, we have identified significant performance disparities, highlighting the need for advancements in models' social understanding capabilities. Our analysis reveals that, in a zero-shot setting, various types of MLLMs generally exhibit difficulties in handling social media tasks. However, MLLMs demonstrate performance improvements post fine-tuning, suggesting potential pathways for improvement.

Automated essay scoring (AES) is a useful tool in English as a Foreign Language (EFL) writing education, offering real-time essay scores for students and instructors. However, previous AES models were trained on essays and scores irrelevant to the practical scenarios of EFL writing education and usually provided a single holistic score due to the lack of appropriate datasets. In this paper, we release DREsS, a large-scale, standard dataset for rubric-based automated essay scoring. DREsS comprises three sub-datasets: DREsS_New, DREsS_Std., and DREsS_CASE. We collect DREsS_New, a real-classroom dataset with 1.7K essays authored by EFL undergraduate students and scored by English education experts. We also standardize existing rubric-based essay scoring datasets as DREsS_Std. We suggest CASE, a corruption-based augmentation strategy for essays, which generates 20K synthetic samples of DREsS_CASE and improves the baseline results by 45.44%. DREsS will enable further research to provide a more accurate and practical AES system for EFL writing education.