Viral 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

[Submitted on 1 Mar 2024 (v1), last revised 19 Nov 2024 (this version, v2)] View a PDF of the paper titled Rethinking cluster-conditioned diffusion models for label-free image synthesis, by Nikolas Adaloglou and Tim Kaiser and Felix Michels and Markus Kollmann View PDF HTML (experimental) Abstract:Diffusion-based image generation models can enhance image quality when conditioned on ground truth labels. Here, we conduct a comprehensive experimental study on image-level conditioning for diffusion models using cluster assignments. We investigate how individual clustering determinants, such as the number of clusters and the clustering method, impact image synthesis across three different datasets. Given the…

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

[Submitted on 24 Jun 2024 (v1), last revised 20 Nov 2024 (this version, v2)] View a PDF of the paper titled From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models, by Sean Welleck and 7 other authors View PDF Abstract:One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during inference. This survey focuses on these inference-time approaches. We explore three areas under a unified mathematical formalism: token-level generation algorithms, meta-generation algorithms,…

arXiv:2411.11935v1 Announce Type: new Abstract: Reliable deep learning models require not only accurate predictions but also well-calibrated confidence estimates to ensure dependable uncertainty estimation. This is crucial in safety-critical applications like autonomous driving, which depend on rapid and precise semantic segmentation of LiDAR point clouds for real-time 3D scene understanding. In this work, we introduce a sampling-free approach for estimating well-calibrated confidence values for classification tasks, achieving alignment with true classification accuracy and significantly reducing inference time compared to sampling-based methods. Our evaluation using the Adaptive Calibration Error (ACE) metric for LiDAR semantic segmentation shows that our approach maintains well-calibrated…

[Submitted on 22 Oct 2024 (v1), last revised 19 Nov 2024 (this version, v2)] View a PDF of the paper titled Literature Meets Data: A Synergistic Approach to Hypothesis Generation, by Haokun Liu and 4 other authors View PDF HTML (experimental) Abstract:AI holds promise for transforming scientific processes, including hypothesis generation. Prior work on hypothesis generation can be broadly categorized into theory-driven and data-driven approaches. While both have proven effective in generating novel and plausible hypotheses, it remains an open question whether they can complement each other. To address this, we develop the first method that combines literature-based insights with…

(CG_dmitriy/Shutterstock) Marimo has emerged from stealth with $5 million in seed funding. The startup has launched an open-source Python notebook designed to provide developers with a tool that is reproducible and Git-friendly. It can also be deployed for production as a web app and executed as a script.  The seed funding round was led by Anthony Goldbloom (ex-Kaggle, Sumble) and Shyam Mani of AIX Ventures, with participation from Jeff Dean (Google), Clement Delangue (HuggingFace), and other notable investors.  Python has been the dominant language in AI. In October 2024, it overtook JavaScript as the most used language in GitHub. As…

We’re excited to announce a new integration between Databricks Notebooks and AI/BI Dashboards, enabling you to effortlessly transform insights from your notebooks into shareable, polished dashboards. This feature reflects our continuous efforts to integrate beautiful, low-code dashboarding into your work across the Databricks platform. This integration allows you to present your notebook analysis in a professional, interactive dashboard and easily share it with business users and stakeholders, across your entire organization.How does this integration work?This new functionality enables you to integrate SQL notebook cells—complete with queries, parameters, and visualizations—into AI/BI Dashboards. It provides practitioners with the best of both worlds:…

arXiv:2411.12913v1 Announce Type: new Abstract: Domain generalization on graphs aims to develop models with robust generalization capabilities, ensuring effective performance on the testing set despite disparities between testing and training distributions. However, existing methods often rely on static encoders directly applied to the target domain, constraining its flexible adaptability. In contrast to conventional methodologies, which concentrate on developing specific generalized models, our framework, MLDGG, endeavors to achieve adaptable generalization across diverse domains by integrating cross-multi-domain meta-learning with structure learning and semantic identification. Initially, it introduces a generalized structure learner to mitigate the adverse effects of task-unrelated edges, enhancing the comprehensiveness…

[Submitted on 27 Apr 2023 (v1), last revised 18 Nov 2024 (this version, v4)] View a PDF of the paper titled SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity Recognition, by Naga VS Raviteja Chappa and 6 other authors View PDF HTML (experimental) Abstract:This paper introduces a novel approach to Social Group Activity Recognition (SoGAR) using Self-supervised Transformers network that can effectively utilize unlabeled video data. To extract spatio-temporal information, we created local and global views with varying frame rates. Our self-supervised objective ensures that features extracted from contrasting views of the same video were consistent across spatio-temporal domains. Our proposed…