Author: Ethan Clark

Authors: Valentinos Pariza、Mohammadreza Salehi、Gertjan Burghouts、Francesco Locatello、Yuki M. Asano Paper: https://arxiv.org/abs/2408.11054 NeCo: Enhancing DINOv2’s Spatial Representations with Patch Neighbor Consistency Introduction Dense self-supervised learning has made significant strides in training feature extractors to produce representations for every pixel or patch of an image without supervision. This advancement has notably improved unsupervised semantic segmentation, object-centric representation learning, and other dense downstream tasks. A recent approach by Balazevic et al. proposed solving semantic segmentation as a nearest-neighbor retrieval problem using spatial patch features. Inspired by this, the authors of the paper introduce NeCo (Patch Neighbor Consistency), a novel training loss that enforces patch-level…

Authors: Xinyu Ning Paper: https://arxiv.org/abs/2408.09158 Introduction Background Spatial-temporal forecasting, particularly in traffic prediction, has garnered significant attention due to its complex correlations in both space and time dimensions. Traditional methods often treat road networks as spatial-temporal graphs, addressing spatial and temporal representations independently. However, these approaches face challenges in capturing the dynamic topology of road networks, dealing with message passing mechanisms, and learning spatial and temporal relationships separately. Problem Statement Existing methods struggle with: 1. Capturing the dynamic topology of road networks. 2. Overcoming the over-smoothing problem in Graph Neural Networks (GNNs). 3. Learning spatial and temporal relationships separately, which…

Authors: Zhengdong Luo Paper: https://arxiv.org/abs/2408.08915 Introduction Supply Chain Finance (SCF) plays a crucial role in enhancing supply chain competitiveness by optimizing capital flow. The advent of Blockchain technology, with its features of data integrity, authenticity, privacy, and information sharing, has the potential to revolutionize SCF. This survey aims to provide a comprehensive overview of Blockchain-based SCF, summarizing current applications and proposing future research directions. Supply Chain Finance Supply Chain Finance Overview Global trade globalization has complicated supply chain mechanisms, putting pressure on capital flow. Large enterprises often dominate supply chains, causing financing difficulties for Small and Medium Enterprises (SMEs). SCF…

Authors: Huy-Son Nguyen、Tuan-Nghia Bui、Long-Hai Nguyen、Hoang Manh-Hung、Cam-Van Thi Nguyen、Hoang-Quynh Le、Duc-Trong Le Paper: https://arxiv.org/abs/2408.08906 Introduction In the realm of e-commerce, recommendation systems play a pivotal role in enhancing user experiences and driving business strategies. Traditional recommendation systems often focus on suggesting individual items, but bundle recommendations, which involve suggesting sets of interconnected items, have emerged as a superior strategic marketing tactic. Bundle recommendations can significantly enhance business profitability and user convenience by grouping relevant items together, such as assortments of detective books or complementary items like a phone with a case. However, recommending bundles based on user preferences poses greater challenges compared…

Authors: Le Xue、Manli Shu、Anas Awadalla、Jun Wang、An Yan、Senthil Purushwalkam、Honglu Zhou、Viraj Prabhu、Yutong Dai、Michael S Ryoo、Shrikant Kendre、Jieyu Zhang、Can Qin、Shu Zhang、Chia-Chih Chen、Ning Yu、Juntao Tan、Tulika Manoj Awalgaonkar、Shelby Heinecke、Huan Wang、Yejin Choi、Ludwig Schmidt、Zeyuan Chen、Silvio Savarese、Juan Carlos Niebles、Caiming Xiong、Ran Xu Paper: https://arxiv.org/abs/2408.08872 Introduction Large Multimodal Models (LMMs) have garnered significant interest due to their potential applications and emergent capabilities. Despite recent advancements in both proprietary and open-source LMMs, there remains a gap in access to open weights, training recipes, and curated datasets. This gap hinders the open-source community from replicating, understanding, and improving LMMs. To address these challenges, the xGen-MM (BLIP-3) framework is introduced, which scales up LMM…

Authors: Kazuki Watanabe、Noboru Isobe Paper: https://arxiv.org/abs/2408.08550 String Diagram of Optimal Transports: A Detailed Interpretive Blog Introduction Optimal transport (OT) is a classical problem in operations research, initially formulated by Kantrovich in 1942. It involves computing the minimum transportation cost between two discrete distributions. This problem has applications in various fields, including artificial intelligence and hierarchical reinforcement learning. In real-world scenarios, models often have hierarchical structures, such as buildings consisting of rooms or maps consisting of streets. String diagrams, a graphical language, can naturally capture these hierarchical structures using two algebraic compositions: sequential composition (#) and parallel composition (⊗). In this…

Authors: Tess Watt、Christos Chrysoulas、Peter J Barclay Paper: https://arxiv.org/abs/2408.08215 Introduction Artificial intelligence (AI) assistants have become invaluable in the healthcare domain, aiding in tasks such as diagnosis and patient monitoring. However, their reliance on internet connectivity limits their usability in remote and low-connectivity areas. According to a United Nations report, approximately 37% of the world’s population has never used the internet, highlighting the need for solutions that do not depend on cloud connectivity. TinyML, which involves deploying machine learning (ML) algorithms on small, constrained devices, offers a promising solution. This study explores the feasibility of using tinyML to provide healthcare support…

Authors: Nikita Makarov、Santhanakrishnan Narayanan、Constantinos Antoniou Paper: https://arxiv.org/abs/2408.07726 Graph Neural Network Surrogate for Strategic Transport Planning Introduction Transportation is a cornerstone of modern society, with urban environments becoming increasingly complex. This complexity poses significant challenges for accurately modeling and simulating transportation systems. Surrogate models have emerged as a promising approach to address these challenges, offering easier application and sometimes even surpassing the performance of traditional models. This paper builds upon previous work by exploring advanced Graph Neural Network (GNN) architectures as surrogate models for strategic transport planning. Specifically, it compares Graph Convolution Networks (GCN) with Graph Attention Networks (GAT) and introduces…