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 176–200 of 1854 papers

TitleStatusHype
DLF: Disentangled-Language-Focused Multimodal Sentiment AnalysisCode2
OmniPrism: Learning Disentangled Visual Concept for Image Generation—0
Unpaired Multi-Domain Histopathology Virtual Staining using Dual Path Prompted InversionCode1
VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping—0
GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic ExpressionCode1
Feat2GS: Probing Visual Foundation Models with Gaussian Splatting—0
FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers—0
Disentanglement and Compositionality of Letter Identity and Letter Position in Variational Auto-Encoder Vision Models—0
FaceTracer: Unveiling Source Identities from Swapped Face Images and Videos for Fraud Prevention—0
Biological Brain Age Estimation using Sex-Aware Adversarial Variational Autoencoder with Multimodal Neuroimages—0
Variational Encoder-Decoders for Learning Latent Representations of Physical Systems—0
Fully Distributed, Flexible Compositional Visual Representations via Soft Tensor ProductsCode0
IF-MDM: Implicit Face Motion Diffusion Model for High-Fidelity Realtime Talking Head Generation—0
D-LORD for Motion Stylization—0
Deformation-Aware Segmentation Network Robust to Motion Artifacts for Brain Tissue Segmentation using Disentanglement Learning—0
Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation—0
TimeWalker: Personalized Neural Space for Lifelong Head Avatars—0
Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head SynthesisCode11
Dual Prototyping with Domain and Class Prototypes for Affective Brain-Computer Interface in Unseen Target Conditions—0
Multi-Task Model Merging via Adaptive Weight DisentanglementCode0
Isolating authorship from content with semantic embeddings and contrastive learning—0
R-MTLLMF: Resilient Multi-Task Large Language Model Fusion at the Wireless Edge—0
Towards Robust Cross-Domain Recommendation with Joint Identifiability of User Preference—0
Revisiting DDIM Inversion for Controlling Defect Generation by Disentangling the Background—0
Factorized Visual Tokenization and Generation—0
Show:102550
← PrevPage 8 of 75Next →

No leaderboard results yet.