stp2y

[Submitted on 30 May 2024] View a PDF of the paper titled Enhancing Performance for Highly Imbalanced Medical Data via Data Regularization in a Federated Learning Setting, by Georgios Tsoumplekas and 4 other authors View PDF HTML (experimental) Abstract:The increased availability of medical data has significantly impacted healthcare by enabling the application of machine / deep learning approaches in various instances. However, medical datasets are usually small and scattered across multiple providers, suffer from high class-imbalance, and are subject to stringent data privacy constraints. In this paper, the application of a data regularization algorithm, suitable for learning under high class-imbalance,…

arXiv:2405.20510v1 Announce Type: new Abstract: We present a computational framework that transforms single images into 3D physical objects. The visual geometry of a physical object in an image is determined by three orthogonal attributes: mechanical properties, external forces, and rest-shape geometry. Existing single-view 3D reconstruction methods often overlook this underlying composition, presuming rigidity or neglecting external forces. Consequently, the reconstructed objects fail to withstand real-world physical forces, resulting in instability or undesirable deformation -- diverging from their intended designs as depicted in the image. Our optimization framework addresses this by embedding physical compatibility into the reconstruction process. We explicitly decompose…

arXiv:2405.20495v1 Announce Type: new Abstract: Aligning foundation models is essential for their safe and trustworthy deployment. However, traditional fine-tuning methods are computationally intensive and require updating billions of model parameters. A promising alternative, alignment via decoding, adjusts the response distribution directly without model updates to maximize a target reward $r$, thus providing a lightweight and adaptable framework for alignment. However, principled decoding methods rely on oracle access to an optimal Q-function ($Q^*$), which is often unavailable in practice. Hence, prior SoTA methods either approximate this $Q^*$ using $Q^{pi_{texttt{sft}}}$ (derived from the reference $texttt{SFT}$ model) or rely on short-term rewards, resulting…