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 11–20 of 1854 papers

TitleStatusHype
HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image GenerationCode2
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model DisentanglementCode2
TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance ControlCode2
TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text EncoderCode2
Realistic and Efficient Face Swapping: A Unified Approach with Diffusion ModelsCode2
Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional RepresentationCode2
DiffArtist: Towards Structure and Appearance Controllable Image StylizationCode2
SaMoye: Zero-shot Singing Voice Conversion Model Based on Feature Disentanglement and EnhancementCode2
ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape DisentanglementCode2
Memory MosaicsCode2
Show:102550
← PrevPage 2 of 186Next →

No leaderboard results yet.