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 1351–1375 of 1854 papers

TitleStatusHype
Variational Encoder-Decoders for Learning Latent Representations of Physical Systems—0
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations—0
VarietySound: Timbre-Controllable Video to Sound Generation via Unsupervised Information Disentanglement—0
VaSAB: The variable size adaptive information bottleneck for disentanglement on speech and singing voice—0
VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speech—0
V-Coder: Adaptive AutoEncoder for Semantic Disclosure in Knowledge Graphs—0
Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization—0
Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement—0
VI3DRM:Towards meticulous 3D Reconstruction from Sparse Views via Photo-Realistic Novel View Synthesis—0
Video Autoencoder: self-supervised disentanglement of static 3D structure and motion—0
VideoSPatS: Video SPatiotemporal Splines for Disentangled Occlusion, Appearance and Motion Modeling and Editing—0
Visual Referential Games Further the Emergence of Disentangled Representations—0
VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping—0
VoiceMixer: Adversarial Voice Style Mixup—0
Volumetric Disentanglement for 3D Scene Manipulation—0
VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment—0
VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence—0
Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement—0
Weighted Metamorphosis for registration of images with different topology.—0
We never go out of Style: Motion Disentanglement by Subspace Decomposition of Latent Space—0
What's New? Summarizing Contributions in Scientific Literature—0
When Is Unsupervised Disentanglement Possible?—0
When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners—0
Why disentanglement-based speaker anonymization systems fail at preserving emotions?—0
WordCon: Word-level Typography Control in Scene Text Rendering—0
Show:102550
← PrevPage 55 of 75Next →

No leaderboard results yet.