Viral News - CybAI news

05 Jun

Boosting Vision-Language Models with Transduction

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

05 Jun

#EpiTwitter: Public Health Messaging During the COVID-19 Pandemic

stp2y0 CommentsViral News

arXiv:2406.01866v1 Announce Type: new Abstract: Effective communication during health crises is critical, with social media serving as a key platform for public health experts (PHEs) to engage with the public. However, it also amplifies pseudo-experts promoting contrarian views. Despite its importance, the role of emotional and moral language in PHEs' communication during COVID-19 remains under explored. This study examines how PHEs and pseudo-experts communicated on Twitter during the pandemic, focusing on emotional and moral language and their engagement with political elites. Analyzing tweets from 489 PHEs and 356 pseudo-experts from January 2020 to January 2021, alongside public responses, we identified…

05 Jun

Celebrating Achievements in Data Intelligence: Presenting the 2024 Databricks Data Intelligence Award Finalists

stp2y0 CommentsViral News

The annual Data Team Awards spotlight data teams and the pivotal role they play in business operations across industries and markets. By continually raising the bar, these innovators demonstrate the technology and ingenuity needed to thrive in today’s business world.With more than 200 nominations from around the world, the Data Team Awards underscore the breadth of innovation happening in the data and artificial intelligence spheres. As we look forward to the Data + AI Summit, Databricks is gearing up to showcase these trailblazers and share their journeys of data-driven transformation and innovation.The Data Team Data Intelligence Award honors teams that…

05 Jun

Optimizing the Optimal Weighted Average: Efficient Distributed Sparse Classification

stp2y0 CommentsViral News

arXiv:2406.01753v1 Announce Type: new Abstract: While distributed training is often viewed as a solution to optimizing linear models on increasingly large datasets, inter-machine communication costs of popular distributed approaches can dominate as data dimensionality increases. Recent work on non-interactive algorithms shows that approximate solutions for linear models can be obtained efficiently with only a single round of communication among machines. However, this approximation often degenerates as the number of machines increases. In this paper, building on the recent optimal weighted average method, we introduce a new technique, ACOWA, that allows an extra round of communication to achieve noticeably better approximation…

05 Jun

Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning

stp2y0 CommentsViral News

arXiv:2406.01820v1 Announce Type: new Abstract: Recent advances in neural network pruning have shown how it is possible to reduce the computational costs and memory demands of deep learning models before training. We focus on this framework and propose a new pruning at initialization algorithm that leverages the Neural Tangent Kernel (NTK) theory to align the training dynamics of the sparse network with that of the dense one. Specifically, we show how the usually neglected data-dependent component in the NTK's spectrum can be taken into account by providing an analytical upper bound to the NTK's trace obtained by decomposing neural networks…

05 Jun

Towards Effective Time-Aware Language Representation: Exploring Enhanced Temporal Understanding in Language Models

stp2y0 CommentsViral News

arXiv:2406.01863v1 Announce Type: new Abstract: In the evolving field of Natural Language Processing, understanding the temporal context of text is increasingly crucial. This study investigates methods to incorporate temporal information during pre-training, aiming to achieve effective time-aware language representation for improved performance on time-related tasks. In contrast to common pre-trained models like BERT, which rely on synchronic document collections such as BookCorpus and Wikipedia, our research introduces BiTimeBERT 2.0, a novel language model pre-trained on a temporal news article collection. BiTimeBERT 2.0 utilizes this temporal news collection, focusing on three innovative pre-training objectives: Time-Aware Masked Language Modeling (TAMLM), Document Dating…

05 Jun

Data + AI Summit 2024: A guide to governance and security talks

stp2y0 CommentsViral News

Data + AI Summit 2024 will be held in person and virtually on June 10-13, 2024, with a highly anticipated lineup of keynotes, sessions, demos, workshops, training, and networking events.If you want to learn more about data and AI governance, you've come to the right place. In this blog, we'll provide an overview of the sessions from Databricks, our customers, and our partners within the data governance track. You can explore the full range of Data + AI Summit sessions by visiting our session catalog.Databricks talksKeynoteMark your calendar for the morning of Thursday, June 13, and tune into an action-packed…

05 Jun

Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching

stp2y0 CommentsViral News

arXiv:2406.01733v1 Announce Type: new Abstract: Diffusion Transformers have recently demonstrated unprecedented generative capabilities for various tasks. The encouraging results, however, come with the cost of slow inference, since each denoising step requires inference on a transformer model with a large scale of parameters. In this study, we make an interesting and somehow surprising observation: the computation of a large proportion of layers in the diffusion transformer, through introducing a caching mechanism, can be readily removed even without updating the model parameters. In the case of U-ViT-H/2, for example, we may remove up to 93.68% of the computation in the cache…

05 Jun

Deep asymmetric mixture model for unsupervised cell segmentation

stp2y0 CommentsViral News

arXiv:2406.01815v1 Announce Type: new Abstract: Automated cell segmentation has become increasingly crucial for disease diagnosis and drug discovery, as manual delineation is excessively laborious and subjective. To address this issue with limited manual annotation, researchers have developed semi/unsupervised segmentation approaches. Among these approaches, the Deep Gaussian mixture model plays a vital role due to its capacity to facilitate complex data distributions. However, these models assume that the data follows symmetric normal distributions, which is inapplicable for data that is asymmetrically distributed. These models also obstacles weak generalization capacity and are sensitive to outliers. To address these issues, this paper presents…

05 Jun

Eliciting the Priors of Large Language Models using Iterated In-Context Learning

stp2y0 CommentsViral News

arXiv:2406.01860v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed in real-world settings, understanding the knowledge they implicitly use when making decisions is critical. One way to capture this knowledge is in the form of Bayesian prior distributions. We develop a prompt-based workflow for eliciting prior distributions from LLMs. Our approach is based on iterated learning, a Markov chain Monte Carlo method in which successive inferences are chained in a way that supports sampling from the prior distribution. We validated our method in settings where iterated learning has previously been used to estimate the priors of human…