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 776–800 of 1854 papers

TitleStatusHype
Embodied Multimodal Multitask Learning—0
Fine-grained Style Modeling, Transfer and Prediction in Text-to-Speech Synthesis via Phone-Level Content-Style Disentanglement—0
Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer—0
Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement—0
Flow-based Image-to-Image Translation with Feature Disentanglement—0
Counterfactual Learning-Driven Representation Disentanglement for Search-Enhanced Recommendation—0
FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers—0
AvatarReX: Real-time Expressive Full-body Avatars—0
Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder—0
Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMax—0
Demystifying Inductive Biases for β-VAE Based Architectures—0
Automatic Speech Disentanglement for Voice Conversion using Rank Module and Speech Augmentation—0
Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement—0
Free-Lunch Color-Texture Disentanglement for Stylized Image Generation—0
FreeTuner: Any Subject in Any Style with Training-free Diffusion—0
EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis—0
Frequency Disentangled Features in Neural Image Compression—0
Frequency Disentangled Learning for Segmentation of Midbrain Structures from Quantitative Susceptibility Mapping Data—0
From Images to Point Clouds: An Efficient Solution for Cross-media Blind Quality Assessment without Annotated Training—0
Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis—0
Gait Recognition via Disentangled Representation Learning—0
Gait Recognition via Semi-supervised Disentangled Representation Learning to Identity and Covariate Features—0
GAMA++: Disentangled Geometric Alignment with Adaptive Contrastive Perturbation for Reliable Domain Transfer—0
Counterfactual Explanation for Regression via Disentanglement in Latent Space—0
ED^4: Explicit Data-level Debiasing for Deepfake Detection—0
Show:102550
← PrevPage 32 of 75Next →

No leaderboard results yet.