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
3DFaceShop: Explicitly Controllable 3D-Aware Portrait GenerationCode2
DiffArtist: Towards Structure and Appearance Controllable Image StylizationCode2
Adversarial Latent AutoencodersCode2
Generative Time Series Forecasting with Diffusion, Denoise, and DisentanglementCode2
ContentVec: An Improved Self-Supervised Speech Representation by Disentangling SpeakersCode2
Interpreting the Latent Space of GANs for Semantic Face EditingCode2
Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional RepresentationCode2
MotionCLIP: Exposing Human Motion Generation to CLIP SpaceCode2
Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival PredictionCode2
When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image GenerationCode2
Show:102550
← PrevPage 5 of 186Next →

No leaderboard results yet.