Deep Learning
Benchmarking Counterfactual Image Generation
Generative AI has revolutionised visual content editing, empowering users to effortlessly modify images and videos. However, not all edits are equal.
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering Xiaoxin He
Given a graph with textual attributes, we enable users to'chat with their graph': that
Approximating mutual information of high-dimensional variables using learned representations
However, estimating MI between multidimensional variables is challenging because the number of samples necessary to converge to an accurate estimate scales unfavorably with dimensionality.
Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model Mark Rowland Google DeepMind
CDF Bellman equation, which we expect to be of independent interest.
Scanning Trojaned Models Using Out-of-Distribution Samples
Scanning for trojan (backdoor) in deep neural networks is crucial due to their significant real-world applications.
The iNaturalist Sounds Dataset
A current gap in the acoustic space is a large-scale, fine-grained dataset of species sounds that is easy to download and easy to use.
Molecule Generation with Fragment Retrieval Augmentation Seul Lee
Work done during an internship at NVIDIA.
FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding
Fine urban change segmentation using multi-temporal remote sensing images is essential for understanding human-environment interactions in urban areas.
Universal Sample Coding
This is known as'channel simulation' or'reverse Shannon coding' (Bennett et al.,