Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification

Kavli Affiliate: Feng Wang | First 5 Authors: Bohan Li, Xiao Xu, Xinghao Wang, Yutai Hou, Yunlong Feng | Summary: Existing image augmentation methods consist of two categories: perturbation-based methods and generative methods. Perturbation-based methods apply pre-defined perturbations to augment an original image, but only locally vary the image, thus lacking image diversity. In contrast, […]


Continue.. Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification

Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification

Kavli Affiliate: Feng Wang | First 5 Authors: Bohan Li, Xiao Xu, Xinghao Wang, Yutai Hou, Yunlong Feng | Summary: Existing image augmentation methods consist of two categories: perturbation-based methods and generative methods. Perturbation-based methods apply pre-defined perturbations to augment an original image, but only locally vary the image, thus lacking image diversity. In contrast, […]


Continue.. Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification

Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment

Kavli Affiliate: Xiang Zhang | First 5 Authors: Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang Wang, | Summary: Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critical input elements, like nodes or edges, that the target GNN relies upon for making […]


Continue.. Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment

Continuous Trajectory Optimization via B-splines for Multi-jointed Robotic Systems

Kavli Affiliate: Ting Xu | First 5 Authors: Changhao Wang, Ting Xu, Masayoshi Tomizuka, , | Summary: Continuous formulations of trajectory planning problems have two main benefits. First, constraints are guaranteed to be satisfied at all times. Secondly, dynamic obstacles can be naturally considered with time. This paper introduces a novel B-spline based trajectory optimization […]


Continue.. Continuous Trajectory Optimization via B-splines for Multi-jointed Robotic Systems

Structured information extraction from complex scientific text with fine-tuned large language models

Kavli Affiliate: Kristin Persson | First 5 Authors: Alexander Dunn, John Dagdelen, Nicholas Walker, Sanghoon Lee, Andrew S. Rosen | Summary: Intelligently extracting and linking complex scientific information from unstructured text is a challenging endeavor particularly for those inexperienced with natural language processing. Here, we present a simple sequence-to-sequence approach to joint named entity recognition […]


Continue.. Structured information extraction from complex scientific text with fine-tuned large language models