Viral News

[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…

arXiv:2411.12946v1 Announce Type: new Abstract: Large Language Models are prone to off-topic misuse, where users may prompt these models to perform tasks beyond their intended scope. Current guardrails, which often rely on curated examples or custom classifiers, suffer from high false-positive rates, limited adaptability, and the impracticality of requiring real-world data that is not available in pre-production. In this paper, we introduce a flexible, data-free guardrail development methodology that addresses these challenges. By thoroughly defining the problem space qualitatively and passing this to an LLM to generate diverse prompts, we construct a synthetic dataset to benchmark and train off-topic guardrails…

[Submitted on 5 Sep 2021 (v1), last revised 20 Nov 2024 (this version, v2)] View a PDF of the paper titled DexRay: A Simple, yet Effective Deep Learning Approach to Android Malware Detection based on Image Representation of Bytecode, by Nadia Daoudi and 5 other authors View PDF HTML (experimental) Abstract:Computer vision has witnessed several advances in recent years, with unprecedented performance provided by deep representation learning research. Image formats thus appear attractive to other fields such as malware detection, where deep learning on images alleviates the need for comprehensively hand-crafted features generalising to different malware variants. We postulate that…

arXiv:2411.11934v1 Announce Type: new Abstract: Stereo video synthesis from a monocular input is a demanding task in the fields of spatial computing and virtual reality. The main challenges of this task lie on the insufficiency of high-quality paired stereo videos for training and the difficulty of maintaining the spatio-temporal consistency between frames. Existing methods primarily address these issues by directly applying novel view synthesis (NVS) techniques to video, while facing limitations such as the inability to effectively represent dynamic scenes and the requirement for large amounts of training data. In this paper, we introduce a novel self-supervised stereo video synthesis…

[Submitted on 8 Dec 2023 (v1), last revised 20 Nov 2024 (this version, v5)] View a PDF of the paper titled Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation, by Jian Gu and 3 other authors View PDF Abstract:Language Models (LMs) have become widely used in software engineering, especially for tasks such as code generation, where they are referred to as code LMs. These models have proven effective in generating code, making it easier for developers to automate coding activities. However, research has highlighted a significant limitation: despite their effectiveness, LMs often produce code that is incorrect, buggy,…

[Submitted on 19 Nov 2024] View a PDF of the paper titled Tree Species Classification using Machine Learning and 3D Tomographic SAR -- a case study in Northern Europe, by Colverd Grace and 4 other authors View PDF HTML (experimental) Abstract:Tree species classification plays an important role in nature conservation, forest inventories, forest management, and the protection of endangered species. Over the past four decades, remote sensing technologies have been extensively utilized for tree species classification, with Synthetic Aperture Radar (SAR) emerging as a key technique. In this study, we employed TomoSense, a 3D tomographic dataset, which utilizes a stack…