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 821–830 of 1854 papers

TitleStatusHype
Dynamic Activation with Knowledge Distillation for Energy-Efficient Spiking NN Ensembles—0
Generative Deformable Radiance Fields for Disentangled Image Synthesis of Topology-Varying Objects—0
A Unified Framework for Biphasic Facial Age Translation with Noisy-Semantic Guided Generative Adversarial Networks—0
Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptation—0
Disentanglement of Emotional Style and Speaker Identity for Expressive Voice Conversion—0
GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech—0
GenSync: A Generalized Talking Head Framework for Audio-driven Multi-Subject Lip-Sync using 3D Gaussian Splatting—0
Differentiable Disentanglement Filter: an Application Agnostic Core Concept Discovery Probe—0
Geometric Disentanglement by Random Convex Polytopes—0
A Unified Framework for Adaptive Representation Enhancement and Inversed Learning in Cross-Domain Recommendation—0
Show:102550
← PrevPage 83 of 186Next →

No leaderboard results yet.