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 981–990 of 1854 papers

TitleStatusHype
Text2Avatar: Text to 3D Human Avatar Generation with Codebook-Driven Body Controllable Attribute—0
Text Attribute Control via Closed-Loop Disentanglement—0
Text Classification and Clustering with Annealing Soft Nearest Neighbor Loss—0
Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editing—0
The Branch Not Taken: Predicting Branching in Online Conversations—0
The Interpretability of Codebooks in Model-Based Reinforcement Learning is Limited—0
The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement—0
TimeWalker: Personalized Neural Space for Lifelong Head Avatars—0
TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation—0
Tooth Instance Segmentation from Cone-Beam CT Images through Point-based Detection and Gaussian Disentanglement—0
Show:102550
← PrevPage 99 of 186Next →

No leaderboard results yet.