Author: Grace Collins

Authors: Linlin Hu、Ao Sun、Shijie Hao、Richang Hong、Meng Wang Paper: https://arxiv.org/abs/2408.10934 Introduction Low-light image enhancement is a crucial task in both academic and industrial communities, aiming to improve the visibility of images captured in low-light conditions. Traditional methods, such as histogram equalization and Retinex-based approaches, have been used extensively but often produce suboptimal results. Recent advancements in deep learning have led to significant improvements in this field, primarily focusing on single-image enhancement. However, these methods often neglect the rich information available in stereo images, which can provide additional depth and disparity information. In this context, stereo image enhancement methods have emerged, leveraging…

Authors: Maxim Ifergan、Leshem Choshen、Roee Aharoni、Idan Szpektor、Omri Abend Paper: https://arxiv.org/abs/2408.10646 Introduction Pretrained large language models (LLMs) have shown an impressive ability to encode and retrieve factual knowledge across various languages. However, there is a significant variation in their performance across different languages, with a noticeable bias towards high-resource languages. This inconsistency raises questions about how LLMs represent factual knowledge in different languages. Do they store distinct knowledge copies for each language, or do they use a single, shared representation of the factual knowledge that is decoded into different languages? This study explores multilingual factual knowledge through two main aspects: the model’s…

Authors: Hendrik Alsmeier、Anton Savchenko、Rolf Findeisen Paper: https://arxiv.org/abs/2408.09781 Introduction Model Predictive Control (MPC) has become a cornerstone in various industries, from autonomous driving to chemical plants, due to its flexibility and ability to handle constraints while optimizing performance. However, the computational demands of MPC can be prohibitive, especially for fast-evolving systems or those with extensive state dimensions. This paper introduces a novel approach to alleviate these computational burdens by integrating neural networks into the MPC framework, thereby enhancing efficiency without compromising safety or performance. Related Work Traditional MPC Approaches MPC’s real-time feasibility can be compromised when dealing with complex systems or…

Authors: Junho Moon、Haejun Chung、Ikbeom Jang Paper: https://arxiv.org/abs/2408.10060 Introduction Facial wrinkle detection is a critical aspect of cosmetic dermatology, serving as an indicator of aging and skin health. However, manual segmentation of facial wrinkles is a challenging and time-consuming task, often leading to inconsistent results due to subjectivity among graders. To address these issues, the study proposes two main solutions: the creation of a public facial wrinkle dataset and a novel training strategy for U-Net-like encoder-decoder models to automatically detect facial wrinkles. Related Work Deep Learning-Based Facial Wrinkle Segmentation Deep learning methods have been increasingly applied to facial wrinkle segmentation. Kim…

Authors: Linhao Yu、Yongqi Leng、Yufei Huang、Shang Wu、Haixin Liu、Xinmeng Ji、Jiahui Zhao、Jinwang Song、Tingting Cui、Xiaoqing Cheng、Tao Liu、Deyi Xiong Paper: https://arxiv.org/abs/2408.09819 Introduction In recent years, large language models (LLMs) have made significant strides in natural language understanding and generation. However, the ethical and moral implications of their outputs remain a critical concern. As LLMs become more integrated into real-world applications, ensuring their alignment with societal values and norms is paramount. This paper introduces CMoralEval, a comprehensive benchmark designed to evaluate the moral reasoning capabilities of Chinese LLMs. The dataset is derived from diverse sources, including a Chinese TV program and various newspapers and academic papers,…

Authors: Yukun Zhang Paper: https://arxiv.org/abs/2408.09523 Introduction Background The Transformer model, introduced by Vaswani et al. in 2017, has revolutionized the field of Natural Language Processing (NLP). Its architecture, characterized by self-attention mechanisms and the ability to handle long-range dependencies, has made it the backbone of numerous state-of-the-art systems in tasks such as machine translation, text summarization, and text generation. Despite its success, the Transformer model’s complexity poses significant challenges in terms of interpretability. Understanding how information flows and transforms within the multi-layered architecture of Transformers remains a daunting task. Research Motivation and Objectives Current interpretability methods for Transformer models often…

Authors: Meng Luo、Hao Fei、Bobo Li、Shengqiong Wu、Qian Liu、Soujanya Poria、Erik Cambria、Mong-Li Lee、Wynne Hsu Paper: https://arxiv.org/abs/2408.09481 Introduction Background and Motivation The quest for human-level artificial intelligence encompasses not only possessing intelligence but also understanding human emotions, thus propelling sentiment analysis and opinion mining to become key areas of research focus. Through decades of research, sentiment analysis has seen significant developments across various dimensions and aspects. The field has evolved from traditional coarse-grained analysis, such as document and sentence-level analysis, to fine-grained analysis (e.g., Aspect-based Sentiment Analysis, ABSA), incorporating a wide array of emotional elements and evolving to extract different sentiment tuples, including the…

Authors: Milan Papež、Martin Rektoris、Václav Šmídl、Tomáš Pevný Paper: https://arxiv.org/abs/2408.09451 Introduction Graphs are a fundamental framework for representing real or abstract objects and their hierarchical interactions in a diverse range of scientific and engineering applications. These include discovering new materials, developing personalized diagnostic strategies, and estimating time of arrival. However, designing probabilistic models for graphs is challenging due to their highly complex and combinatorial structures. Traditional approaches often struggle to handle this complexity effectively. Deep generative models, which rely on expressive graph neural networks, have recently made significant progress in capturing complex probability distributions over graphs. However, these models are intractable and…

Authors: Mahrukh Siddiqui、Shahzaib Iqbal、Bandar AlShammari、Bandar Alhaqbani、Tariq M. Khan、Imran Razzak Paper: https://arxiv.org/abs/2408.09426 Introduction In recent years, contactless biometric technologies have garnered significant attention due to advancements in sensing technologies and their applications in commercial sectors. The National Institute of Standards and Technology (NIST) has emphasized the development of Next Generation Fingerprint Technologies, highlighting the potential of contactless fingerprint systems. Unlike traditional contact-based fingerprint systems, contactless systems offer several advantages, including reduced contamination, minimized non-linear distortion, and improved hygiene. However, contactless fingerprint images present unique challenges, such as low ridge/valley contrast and the absence of elastic deformation, which complicate the enhancement and…

Authors: Lei Zhang、Jin Pan、Jacob Gettig、Steve Oney、Anhong Guo Paper: https://arxiv.org/abs/2408.09382 Introduction As Virtual Reality (VR) continues to gain traction in various fields such as education, gaming, and spatial design, the need for effective tools to create high-quality 3D scenes becomes increasingly important. Immersive authoring allows users to create and evaluate 3D scenes directly within a virtual environment, leveraging their spatial capabilities. However, the manual creation of 3D layouts can be tedious and time-consuming, limiting the exploration of diverse ideas. Recent advances in generative AI models offer a promising solution by enabling the automatic creation of realistic 3D layouts. This study introduces…