Viral News - CybAI news

21 Nov

A Foundation Model for Unified Urban Spatio-Temporal Flow Prediction

stp2y0 CommentsViral News

arXiv:2411.12972v1 Announce Type: new Abstract: Urban spatio-temporal flow prediction, encompassing traffic flows and crowd flows, is crucial for optimizing city infrastructure and managing traffic and emergency responses. Traditional approaches have relied on separate models tailored to either grid-based data, representing cities as uniform cells, or graph-based data, modeling cities as networks of nodes and edges. In this paper, we build UniFlow, a foundational model for general urban flow prediction that unifies both grid-based and graphbased data. We first design a multi-view spatio-temporal patching mechanism to standardize different data into a consistent sequential format and then introduce a spatio-temporal transformer architecture…

21 Nov

Analyzing and Improving the Skin Tone Consistency and Bias in Implicit 3D Relightable Face Generators

stp2y0 CommentsViral News

arXiv:2411.12002v1 Announce Type: new Abstract: With the advances in generative adversarial networks (GANs) and neural rendering, 3D relightable face generation has received significant attention. Among the existing methods, a particularly successful technique uses an implicit lighting representation and generates relit images through the product of synthesized albedo and light-dependent shading images. While this approach produces high-quality results with intricate shading details, it often has difficulty producing relit images with consistent skin tones, particularly when the lighting condition is extracted from images of individuals with dark skin. Additionally, this technique is biased towards producing albedo images with lighter skin tones. Our…

21 Nov

Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning

stp2y0 CommentsViral News

[Submitted on 17 Apr 2024 (v1), last revised 19 Nov 2024 (this version, v2)] View a PDF of the paper titled Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning, by Xuechen Zhang and 5 other authors View PDF HTML (experimental) Abstract:Recent successes in natural language processing have led to the proliferation of large language models (LLMs) by multiple providers. Each LLM offering has different inference accuracy, monetary cost, and latency, and their accuracy further depends on the exact wording of the question (i.e., the specific prompt). At the same time, users often have a limit on monetary budget and latency…

21 Nov

Delegating Data Collection in Decentralized Machine Learning

stp2y0 CommentsViral News

[Submitted on 4 Sep 2023 (v1), last revised 20 Nov 2024 (this version, v3)] View a PDF of the paper titled Delegating Data Collection in Decentralized Machine Learning, by Nivasini Ananthakrishnan and 3 other authors View PDF HTML (experimental) Abstract:Motivated by the emergence of decentralized machine learning (ML) ecosystems, we study the delegation of data collection. Taking the field of contract theory as our starting point, we design optimal and near-optimal contracts that deal with two fundamental information asymmetries that arise in decentralized ML: uncertainty in the assessment of model quality and uncertainty regarding the optimal performance of any model.…

21 Nov

3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning

stp2y0 CommentsViral News

[Submitted on 19 Aug 2024 (v1), last revised 19 Nov 2024 (this version, v3)] View a PDF of the paper titled 3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning, by Haoyu Zhao and 3 other authors View PDF HTML (experimental) Abstract:Existing approaches for human avatar generation--both NeRF-based and 3D Gaussian Splatting (3DGS) based--struggle with maintaining 3D consistency and exhibit degraded detail reconstruction, particularly when training with sparse inputs. To address this challenge, we propose CHASE, a novel framework that achieves dense-input-level performance using only sparse inputs through two key innovations: cross-pose intrinsic 3D consistency supervision and…

21 Nov

Song Form-aware Full-Song Text-to-Lyrics Generation with Multi-Level Granularity Syllable Count Control

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

Machine learned reconstruction of tsunami dynamics from sparse observations

stp2y0 CommentsViral News

arXiv:2411.12948v1 Announce Type: new Abstract: We investigate the use of the Senseiver, a transformer neural network designed for sparse sensing applications, to estimate full-field surface height measurements of tsunami waves from sparse observations. The model is trained on a large ensemble of simulated data generated via a shallow water equations solver, which we show to be a faithful reproduction for the underlying dynamics by comparison to historical events. We train the model on a dataset consisting of 8 tsunami simulations whose epicenters correspond to historical USGS earthquake records, and where the model inputs are restricted to measurements obtained at actively…

21 Nov

Medical Video Generation for Disease Progression Simulation

stp2y0 CommentsViral News

arXiv:2411.11943v1 Announce Type: new Abstract: Modeling disease progression is crucial for improving the quality and efficacy of clinical diagnosis and prognosis, but it is often hindered by a lack of longitudinal medical image monitoring for individual patients. To address this challenge, we propose the first Medical Video Generation (MVG) framework that enables controlled manipulation of disease-related image and video features, allowing precise, realistic, and personalized simulations of disease progression. Our approach begins by leveraging large language models (LLMs) to recaption prompt for disease trajectory. Next, a controllable multi-round diffusion model simulates the disease progression state for each patient, creating realistic…

21 Nov

WaterPark: A Robustness Assessment of Language Model Watermarking

stp2y0 CommentsViral News

arXiv:2411.13425v1 Announce Type: cross Abstract: To mitigate the misuse of large language models (LLMs), such as disinformation, automated phishing, and academic cheating, there is a pressing need for the capability of identifying LLM-generated texts. Watermarking emerges as one promising solution: it plants statistical signals into LLMs' generative processes and subsequently verifies whether LLMs produce given texts. Various watermarking methods (``watermarkers'') have been proposed; yet, due to the lack of unified evaluation platforms, many critical questions remain under-explored: i) What are the strengths/limitations of various watermarkers, especially their attack robustness? ii) How do various design choices impact their robustness? iii) How…

21 Nov

UCSD’s New SCIDS School: All About the Apps

stp2y0 CommentsViral News

San Diego Supercomputer Center/Image courtesy SDSC) Some research universities excel in exploring intellectual possibilities and postulating abstract theories. Those terms aren’t likely to be associated with the University of California, San Diego’s new School of Computing, Information and Data Sciences (SCIDS), which is all about taking the power of data and computer science and applying it to solve problems in the real world. SCIDS was officially formed last month by the union of the San Diego Supercomputer Center (SDSC) and the Halıcıoğlu Data Science Institute (HDSI). As the fourth school on the rapidly expanding UC campus, SCIDS is generating quite…