Viral News - CybAI news

19 Nov

A Comprehensive Study of Knowledge Editing for Large Language Models

stp2y0 CommentsViral News

[Submitted on 2 Jan 2024 (v1), last revised 17 Nov 2024 (this version, v5)] Authors:Ningyu Zhang, Yunzhi Yao, Bozhong Tian, Peng Wang, Shumin Deng, Mengru Wang, Zekun Xi, Shengyu Mao, Jintian Zhang, Yuansheng Ni, Siyuan Cheng, Ziwen Xu, Xin Xu, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Lei Liang, Zhiqiang Zhang, Xiaowei Zhu, Jun Zhou, Huajun Chen View a PDF of the paper titled A Comprehensive Study of Knowledge Editing for Large Language Models, by Ningyu Zhang and 21 other authors View PDF HTML (experimental) Abstract:Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that…

19 Nov

Pedal Power: Lessons in Thriving Through Change

stp2y0 CommentsViral News

The below is a summary of my recent story about how to thrive in a changing world. What do cycling 14,000 km across Australia and navigating exponential change have in common? More than you’d think-both demand grit, adaptability, and a clear vision. In 2011, I embarked on a journey to cycle 14,122 km around Australia in 100 days, aiming to raise 25,000 for children’s cancer charity KiKa. What began as a daunting physical challenge turned into a profound lesson in resilience, adaptability, and vision. Traversing the harsh Nullarbor Plain and battling unrelenting headwinds tested not just my body but my…

19 Nov

Towards Robust Text Classification: Mitigating Spurious Correlations with Causal Learning

stp2y0 CommentsViral News

[Submitted on 1 Nov 2024 (v1), last revised 16 Nov 2024 (this version, v2)] View a PDF of the paper titled Towards Robust Text Classification: Mitigating Spurious Correlations with Causal Learning, by Yuqing Zhou and 1 other authors View PDF HTML (experimental) Abstract:In text classification tasks, models often rely on spurious correlations for predictions, incorrectly associating irrelevant features with the target labels. This issue limits the robustness and generalization of models, especially when faced with out-of-distribution data where such spurious correlations no longer hold. To address this challenge, we propose the Causally Calibrated Robust Classifier (CCR), which aims to reduce…

19 Nov

Enhancing Cross-Modal Contextual Congruence for Crowdfunding Success using Knowledge-infused Learning

stp2y0 CommentsViral News

[Submitted on 6 Feb 2024 (v1), last revised 17 Nov 2024 (this version, v2)] View a PDF of the paper titled Enhancing Cross-Modal Contextual Congruence for Crowdfunding Success using Knowledge-infused Learning, by Trilok Padhi and 4 other authors View PDF HTML (experimental) Abstract:The digital landscape continually evolves with multimodality, enriching the online experience for users. Creators and marketers aim to weave subtle contextual cues from various modalities into congruent content to engage users with a harmonious message. This interplay of multimodal cues is often a crucial factor in attracting users' attention. However, this richness of multimodality presents a challenge to…

19 Nov

Hybrid Querying Over Relational Databases and Large Language Models

stp2y0 CommentsViral News

[Submitted on 1 Aug 2024 (v1), last revised 15 Nov 2024 (this version, v2)] View a PDF of the paper titled Hybrid Querying Over Relational Databases and Large Language Models, by Fuheng Zhao and 2 other authors View PDF HTML (experimental) Abstract:Database queries traditionally operate under the closed-world assumption, providing no answers to questions that require information beyond the data stored in the database. Hybrid querying using SQL offers an alternative by integrating relational databases with large language models (LLMs) to answer beyond-database questions. In this paper, we present the first cross-domain benchmark, SWAN, containing 120 beyond-database questions over four…

19 Nov

Spatio-Temporal Jump Model for Urban Thermal Comfort Monitoring

stp2y0 CommentsViral News

[Submitted on 14 Nov 2024 (v1), last revised 18 Nov 2024 (this version, v2)] View a PDF of the paper titled Spatio-Temporal Jump Model for Urban Thermal Comfort Monitoring, by Federico P. Cortese and 1 other authors View PDF HTML (experimental) Abstract:Thermal comfort is essential for well-being in urban spaces, especially as cities face increasing heat from urbanization and climate change. Existing thermal comfort models usually overlook temporal dynamics alongside spatial dependencies. We address this problem by introducing a spatio-temporal jump model that clusters data with persistence across both spatial and temporal dimensions. This framework enhances interpretability, minimizes abrupt state…

19 Nov

Equivariant spatio-hemispherical networks for diffusion MRI deconvolution

stp2y0 CommentsViral News

arXiv:2411.11819v1 Announce Type: cross Abstract: Each voxel in a diffusion MRI (dMRI) image contains a spherical signal corresponding to the direction and strength of water diffusion in the brain. This paper advances the analysis of such spatio-spherical data by developing convolutional network layers that are equivariant to the $mathbf{E(3) times SO(3)}$ group and account for the physical symmetries of dMRI including rotations, translations, and reflections of space alongside voxel-wise rotations. Further, neuronal fibers are typically antipodally symmetric, a fact we leverage to construct highly efficient spatio-hemispherical graph convolutions to accelerate the analysis of high-dimensional dMRI data. In the context of…

19 Nov

MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models

stp2y0 CommentsViral News

[Submitted on 10 Jun 2024 (v1), last revised 16 Nov 2024 (this version, v2)] View a PDF of the paper titled MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models, by Zichun Yu and 2 other authors View PDF HTML (experimental) Abstract:Pretraining data selection has the potential to improve language model pretraining efficiency by utilizing higher-quality data from massive web data corpora. Current data selection methods, which rely on either hand-crafted rules or larger reference models, are conducted statically and do not capture the evolving data preferences during pretraining. In this paper, we introduce model-aware data selection with…

19 Nov

Leveraging Bi-Focal Perspectives and Granular Feature Integration for Accurate Reliable Early Alzheimer’s Detection

stp2y0 CommentsViral News

[Submitted on 15 Jul 2024 (v1), last revised 17 Nov 2024 (this version, v3)] View a PDF of the paper titled Leveraging Bi-Focal Perspectives and Granular Feature Integration for Accurate Reliable Early Alzheimer's Detection, by Pandiyaraju V and 5 other authors View PDF HTML (experimental) Abstract:Alzheimer's disease (AD) is the most common neurodegeneration, annually diagnosed in millions of patients. The present medicine scenario still finds challenges in the exact diagnosis and classification of AD through neuroimaging data. Traditional CNNs can extract a good amount of low-level information in an image but fail to extract high-level minuscule particles, which is a…

19 Nov

AppSign: Multi-level Approximate Computing for Real-Time Traffic Sign Recognition in Autonomous Vehicles

stp2y0 CommentsViral News

arXiv:2411.10988v1 Announce Type: cross Abstract: This paper presents a multi-level approximate computing approach for real-time traffic sign recognition in autonomous vehicles called AppSign. Since autonomous vehicles are real-time systems, they must gather environmental information and process them instantaneously to respond properly. However, due to the limited resources of these systems, executing computation-intensive algorithms such as deep-learning schemes that lead to precise output is impossible and takes a long time. To tackle this, imprecise computation schemes compromise the complexity and real-time operations. In this context, AppSign presents a multi-level approximate computing scheme to balance the accuracy and computation cost of the…