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

Showing 4150 of 1854 papers

TitleStatusHype
eVAE: Evolutionary Variational AutoencoderCode2
3DFaceShop: Explicitly Controllable 3D-Aware Portrait GenerationCode2
Generative Time Series Forecasting with Diffusion, Denoise, and DisentanglementCode2
A Style-Based Generator Architecture for Generative Adversarial NetworksCode2
ContentVec: An Improved Self-Supervised Speech Representation by Disentangling SpeakersCode2
Interpreting the Latent Space of GANs for Semantic Face EditingCode2
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face AnimationCode2
MotionCLIP: Exposing Human Motion Generation to CLIP SpaceCode2
BlendFace: Re-designing Identity Encoders for Face-SwappingCode2
When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image GenerationCode2
Show:102550
← PrevPage 5 of 186Next →

No leaderboard results yet.