SOTAVerified

Disentanglement

This is an approach to solve a diverse set of tasks in a data efficient manner by disentangling (or isolating ) the underlying structure of the main problem into disjoint parts of its representations. This disentanglement can be done by focussing on the "transformation" properties of the world(main problem)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 1854 papers

TitleStatusHype
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized TasksCode2
Preserving Fairness Generalization in Deepfake DetectionCode2
Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image SynthesisCode2
DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text AlignmentCode2
Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival PredictionCode2
When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image GenerationCode2
StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style AdapterCode2
BlendFace: Re-designing Identity Encoders for Face-SwappingCode2
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face AnimationCode2
A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild ImagesCode2
Show:102550
← PrevPage 3 of 186Next →

No leaderboard results yet.