UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation

The automated analysis of historical maps has significantly improved due to advancements in deep learning, particularly in computer vision. However, the scarcity of annotated training data for specific historical map corpora poses a challenge. To address this, a method for generating synthetic historical maps by transferring the cartographic style of original maps onto vector data has been proposed, enabling the creation of an unlimited number of training samples for machine learning tasks.

This paper addresses the estimation of inverse covariance, or precision matrix, in high-dimensional settings. It focuses on linear shrinkage estimators and those derived from data augmentation, which enriches datasets with artificial samples before model fitting. The authors derive estimators and provide concentration bounds for their quadratic error, facilitating method comparison and hyperparameter tuning.

FuncBind is a new framework designed for structure-based drug design that utilizes neural fields to generate target-conditioned, all-atom molecules. This approach allows for a unified model capable of handling diverse atomic systems, including small and large molecules, and non-canonical amino acids. FuncBind demonstrates competitive performance in generating various molecular structures, including small molecules and macrocyclic peptides, conditioned on target structures.

The paper introduces Token-Selective Parameter-Efficient Fine-Tuning (TS-PEFT), a novel approach in natural language processing and computer vision that selectively applies modifications to a subset of position indices. This method challenges the traditional Parameter-Efficient Fine-Tuning (PEFT) approach, which indiscriminately modifies all indices. Experimental results indicate that the targeted application of TS-PEFT can enhance performance on downstream tasks, suggesting a shift towards more efficient fine-tuning strategies.

The paper introduces Weighted Integrated Gradients (WG), an advanced method for feature attribution in explainable AI, particularly in computer vision. WG addresses the limitations of Integrated Gradients (IG) by adaptively selecting and weighting baseline images, improving attribution reliability. This method preserves the core properties of IG while enhancing the quality of explanations, making it a significant contribution to the field.