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 51–100 of 1854 papers

TitleStatusHype
Towards a Universal Image Degradation Model via Content-Degradation DisentanglementCode0
TSPulse: Dual Space Tiny Pre-Trained Models for Rapid Time-Series Analysis—0
Unified Architecture and Unsupervised Speech Disentanglement for Speaker Embedding-Free Enrollment in Personalized Speech Enhancement—0
Robust Cross-View Geo-Localization via Content-Viewpoint Disentanglement—0
Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges—0
TT-DF: A Large-Scale Diffusion-Based Dataset and Benchmark for Human Body Forgery DetectionCode1
FedIFL: A federated cross-domain diagnostic framework for motor-driven systems with inconsistent fault modes—0
Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models—0
Towards a Unified Representation Evaluation Framework Beyond Downstream TasksCode0
Cross-Branch Orthogonality for Improved Generalization in Face Deepfake Detection—0
Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D GenerationCode2
Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation—0
DATA: Multi-Disentanglement based Contrastive Learning for Open-World Semi-Supervised Deepfake Attribution—0
Reliable Disentanglement Multi-view Learning Against View Adversarial AttacksCode0
DFVO: Learning Darkness-free Visible and Infrared Image Disentanglement and Fusion All at OnceCode1
Causal Intervention Framework for Variational Auto Encoder Mechanistic Interpretability—0
Panoramic Out-of-Distribution SegmentationCode1
Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement—0
GenSync: A Generalized Talking Head Framework for Audio-driven Multi-Subject Lip-Sync using 3D Gaussian Splatting—0
Improving Editability in Image Generation with Layer-wise Memory—0
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language ModelsCode0
Beyond Whole Dialogue Modeling: Contextual Disentanglement for Conversational Recommendation—0
DRC: Enhancing Personalized Image Generation via Disentangled Representation Composition—0
A Controllable Appearance Representation for Flexible Transfer and Editing—0
Causal Disentanglement for Robust Long-tail Medical Image Generation—0
Human-aligned Deep Learning: Explainability, Causality, and Biological Inspiration—0
ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos—0
DMAGaze: Gaze Estimation Based on Feature Disentanglement and Multi-Scale Attention—0
VAE-based Feature Disentanglement for Data Augmentation and Compression in Generalized GNSS Interference Classification—0
Deconfounded Reasoning for Multimodal Fake News Detection via Causal Intervention—0
TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation—0
Steering CLIP's vision transformer with sparse autoencoders—0
Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical ImagingCode1
VideoSPatS: Video SPatiotemporal Splines for Disentangled Occlusion, Appearance and Motion Modeling and Editing—0
Learning Sparse Disentangled Representations for Multimodal Exclusion Retrieval—0
ConMo: Controllable Motion Disentanglement and Recomposition for Zero-Shot Motion TransferCode0
Efficient Model Editing with Task-Localized Sparse Fine-tuningCode0
EagleVision: Object-level Attribute Multimodal LLM for Remote SensingCode1
Language-Guided Trajectory Traversal in Disentangled Stable Diffusion Latent Space for Factorized Medical Image Generation—0
Unsupervised Feature Disentanglement and Augmentation Network for One-class Face Anti-spoofing—0
DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-IDCode1
CMD-HAR: Cross-Modal Disentanglement for Wearable Human Activity Recognition—0
NeuroLIP: Interpretable and Fair Cross-Modal Alignment of fMRI and Phenotypic Text—0
Exploring Disentangled and Controllable Human Image Synthesis: From End-to-End to Stage-by-Stage—0
SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image PretrainingCode0
DisentTalk: Cross-lingual Talking Face Generation via Semantic Disentangled Diffusion Model—0
Fast and Physically-based Neural Explicit Surface for Relightable Human Avatars—0
Seeing Speech and Sound: Distinguishing and Locating Audios in Visual Scenes—0
Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model—0
Federated Cross-Domain Click-Through Rate Prediction With Large Language Model Augmentation—0
Show:102550
← PrevPage 2 of 38Next →

No leaderboard results yet.