conference
HairDiffusion: VividMulti-Colored HairEditingviaLatentDiffusion
Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using textdescriptions orreference images, while preserving irrelevant attributes(e.g.,identity,background,cloth).
Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound
Hadi Kazemi, Sobhan Soleymani, Fariborz Taherkhani, Seyed Iranmanesh, Nasser Nasrabadi
Neural Information Processing Systems http://nips.cc/
Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance
Neal Jean, Sang Michael Xie, Stefano Ermon
Neural Information Processing Systems http://nips.cc/
Improving Simple Models with Confidence Profiles
Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss, Peder A. Olsen
Neural Information Processing Systems http://nips.cc/
Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization
Bargav Jayaraman, Lingxiao Wang, David Evans, Quanquan Gu
Neural Information Processing Systems http://nips.cc/
Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart Schemes
Junqi Tang, Mohammad Golbabaee, Francis Bach, Mike E. davies
Neural Information Processing Systems http://nips.cc/
FullyExplicitDynamicGaussianSplatting
Meanwhile, a promising alternative, 3DGaussian Splatting (3DGS) [13], has emerged, which achieves photo-realistic rendering results with significantly faster training and rendering speeds.