327 citations · 978 across the 50 of their papers we have counts for
104 papers
DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer
Runjia Li, Junlin Han, Luke Melas-Kyriazi +6
We present DreamBeast, a novel method based on score distillation sampling (SDS) for generating fantastical 3D animal assets composed of distinct parts. Existing SDS methods often…
Select to Perfect: Imitating desired behavior from large multi-agent data
Tim Franzmeyer, Edith Elkind, Philip Torr +2
AI agents are commonly trained with large datasets of demonstrations of human behavior. However, not all behaviors are equally safe or desirable. Desired characteristics for an AI…
Reliable Evaluation of Adversarial Transferability
Wenqian Yu, Jindong Gu, Zhijiang Li +1
Adversarial examples (AEs) with small adversarial perturbations can mislead deep neural networks (DNNs) into wrong predictions. The AEs created on one DNN can also fool another DNN…
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning
Jishnu Mukhoti, Tsung-Yu Lin, Omid Poursaeed +4
We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of t…
Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs
Guangrun Wang, Philip H. S. Torr
Classifiers and generators have long been separated. We break down this separation and showcase that conventional neural network classifiers can generate high-quality images of a l…
LUMix: Improving Mixup by Better Modelling Label Uncertainty
Shuyang Sun, Jie-Neng Chen, Ruifei He +3
Modern deep networks can be better generalized when trained with noisy samples and regularization techniques. Mixup and CutMix have been proven to be effective for data augmentatio…