Viral News - CybAI news

21 Nov

Procurement Auctions via Approximately Optimal Submodular Optimization

stp2y0 CommentsViral News

arXiv:2411.13513v1 Announce Type: cross Abstract: We study procurement auctions, where an auctioneer seeks to acquire services from strategic sellers with private costs. The quality of services is measured by a submodular function known to the auctioneer. Our goal is to design computationally efficient procurement auctions that (approximately) maximize the difference between the quality of the acquired services and the total cost of the sellers, while ensuring incentive compatibility (IC), individual rationality (IR) for sellers, and non-negative surplus (NAS) for the auctioneer. Our contributions are twofold: (i) we provide an improved analysis of existing algorithms for non-positive submodular function maximization, and…

21 Nov

FCC: Fully Connected Correlation for Few-Shot Segmentation

stp2y0 CommentsViral News

arXiv:2411.11917v1 Announce Type: new Abstract: Few-shot segmentation (FSS) aims to segment the target object in a query image using only a small set of support images and masks. Therefore, having strong prior information for the target object using the support set is essential for guiding the initial training of FSS, which leads to the success of few-shot segmentation in challenging cases, such as when the target object shows considerable variation in appearance, texture, or scale across the support and query images. Previous methods have tried to obtain prior information by creating correlation maps from pixel-level correlation on final-layer or same-layer…

21 Nov

TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs

stp2y0 CommentsViral News

[Submitted on 14 Jun 2024 (v1), last revised 20 Nov 2024 (this version, v2)] View a PDF of the paper titled TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs, by Zhuofeng Li and 8 other authors View PDF HTML (experimental) Abstract:Text-Attributed Graphs (TAGs) augment graph structures with natural language descriptions, facilitating detailed depictions of data and their interconnections across various real-world settings. However, existing TAG datasets predominantly feature textual information only at the nodes, with edges typically represented by mere binary or categorical attributes. This lack of rich textual edge annotations significantly limits the exploration of contextual relationships between…

21 Nov

ZNorm: Z-Score Gradient Normalization Accelerating Skip-Connected Network Training without Architectural Modification

stp2y0 CommentsViral News

[Submitted on 2 Aug 2024 (v1), last revised 20 Nov 2024 (this version, v5)] View a PDF of the paper titled ZNorm: Z-Score Gradient Normalization Accelerating Skip-Connected Network Training without Architectural Modification, by Juyoung Yun View PDF HTML (experimental) Abstract:The rapid advancements in deep learning necessitate better training methods for deep neural networks (DNNs). As models grow in complexity, vanishing and exploding gradients impede performance, particularly in skip-connected architectures like Deep Residual Networks. We propose Z-Score Normalization for Gradient Descent (ZNorm), an innovative technique that adjusts only the gradients without modifying the network architecture to accelerate training and improve model…

21 Nov

N-DriverMotion: Driver motion learning and prediction using an event-based camera and directly trained spiking neural networks on Loihi 2

stp2y0 CommentsViral News

[Submitted on 23 Aug 2024 (v1), last revised 18 Nov 2024 (this version, v2)] View a PDF of the paper titled N-DriverMotion: Driver motion learning and prediction using an event-based camera and directly trained spiking neural networks on Loihi 2, by Hyo Jong Chung and 2 other authors View PDF HTML (experimental) Abstract:Driver motion recognition is a principal factor in ensuring the safety of driving systems. This paper presents a novel system for learning and predicting driver motions and an event-based high-resolution (1280x720) dataset, N-DriverMotion, newly collected to train on a neuromorphic vision system. The system comprises an event-based camera…

21 Nov

Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods

stp2y0 CommentsViral News

[Submitted on 18 Nov 2024 (v1), last revised 20 Nov 2024 (this version, v2)] View a PDF of the paper titled Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods, by Jai Doshi and Asa Cooper Stickland View PDF HTML (experimental) Abstract:Large language model unlearning aims to remove harmful information that LLMs have learnt to prevent their use for malicious purposes. LLMU and RMU have been proposed as two methods for LLM unlearning, achieving impressive results on unlearning benchmarks. We study in detail the efficacy of these methods by evaluating their impact on general model capabilities on…

21 Nov

Select High-Level Features: Efficient Experts from a Hierarchical Classification Network

stp2y0 CommentsViral News

[Submitted on 8 Mar 2024 (v1), last revised 20 Nov 2024 (this version, v2)] View a PDF of the paper titled Select High-Level Features: Efficient Experts from a Hierarchical Classification Network, by Andr'e Kelm and 7 other authors View PDF HTML (experimental) Abstract:This study introduces a novel expert generation method that dynamically reduces task and computational complexity without compromising predictive performance. It is based on a new hierarchical classification network topology that combines sequential processing of generic low-level features with parallelism and nesting of high-level features. This structure allows for the innovative extraction technique: the ability to select only high-level…

21 Nov

DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes

stp2y0 CommentsViral News

arXiv:2411.11921v1 Announce Type: new Abstract: We present DeSiRe-GS, a self-supervised gaussian splatting representation, enabling effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios. Our approach employs a two-stage optimization pipeline of dynamic street Gaussians. In the first stage, we extract 2D motion masks based on the observation that 3D Gaussian Splatting inherently can reconstruct only the static regions in dynamic environments. These extracted 2D motion priors are then mapped into the Gaussian space in a differentiable manner, leveraging an efficient formulation of dynamic Gaussians in the second stage. Combined with the introduced geometric regularizations, our method are able…

21 Nov

HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives

stp2y0 CommentsViral News

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol

21 Nov

KX Aims to Unlock Python’s Potential with PyKX 3.0

stp2y0 CommentsViral News

(dTosh/Shutterstock) As AI-driven algorithms become increasingly complex, the demand for scalable solutions that integrate powerful analytical engines with machine learning libraries has surged. KX, a performance analytical database for AI, has responded to this need by enhancing PyKX, its Python-first interface for kdb+, with a new hybrid architecture. PyKX 3.0 merges kdb+’s processing power with Python’s ML capabilities. The company claims that developers can use the platform to build advanced AI-driven applications and analytics without compromising on speed or scalability. In May 2023, KX had open-sourced PyKX, making its kdb+ time-series database and q programming language accessible to the global…