CybAI 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

arXiv:2407.03482v1 Announce Type: new Abstract: Foundation models (FMs) have revolutionized computer vision, enabling effective learning across different domains. However, their performance under domain shift is yet underexplored. This paper investigates the zero-shot domain adaptation potential of FMs by comparing different backbone architectures and introducing novel domain-aware components that leverage domain related textual embeddings. We propose domain adaptive normalization, termed as Domino, which explicitly leverages domain embeddings during fine-tuning, thus making the model domain aware. Ultimately, Domino enables more robust computer vision models that can adapt effectively to various unseen domains. Source link lol

arXiv:2407.03600v1 Announce Type: new Abstract: Rapidly increasing model scales coupled with steering methods such as chain-of-thought prompting have led to drastic improvements in language model reasoning. At the same time, models struggle with compositional generalization and are far from human performance on many reasoning-based benchmarks. Leveraging the success of chain-of-thought prompting, and also taking inspiration from context-aware decoding (CAD), we explore input-based contrasting methods to further encourage the type of reasoning induced by chain-of-thought prompting. While work remains to stabilize these results across datasets and models, the improvements we find warrant further investigation into input-based steering methods for context-aware reasoning.…

We are thrilled to welcome the Prodvana team to Databricks. At Databricks, we are building one of the world’s largest multi-cloud platforms to support unprecedented growth of data and AI workloads. This platform launches more than 20 million virtual machines each day across the three major cloud platforms. It enables our customers to run their data and AI workloads without dealing with infrastructure details – all with enterprise-grade scalability, reliability, and consistency. The infrastructure powering this platform is one of our core competencies.Prodvana has developed innovative methods to simplify the complexities of deployment in cloud-native environments through their managed delivery,…

arXiv:2407.03641v1 Announce Type: new Abstract: Pre-training followed by fine-tuning is widely adopted among practitioners. The performance can be improved by "model soups"~cite{wortsman2022model} via exploring various hyperparameter configurations.The Learned-Soup, a variant of model soups, significantly improves the performance but suffers from substantial memory and time costs due to the requirements of (i) having to load all fine-tuned models simultaneously, and (ii) a large computational graph encompassing all fine-tuned models. In this paper, we propose Memory Efficient Hyperplane Learned Soup (MEHL-Soup) to tackle this issue by formulating the learned soup as a hyperplane optimization problem and introducing block coordinate gradient descent to…