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 76–100 of 1854 papers

TitleStatusHype
Enhancing Knowledge Tracing with Concept Map and Response DisentanglementCode1
VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors EmbeddingCode1
Barbie: Text to Barbie-Style 3D AvatarsCode1
Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight DisentanglementCode1
Mamba? Catch The Hype Or Rethink What Really Helps for Image RegistrationCode1
A New Dataset and Framework for Real-World Blurred Images Super-ResolutionCode1
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational AutoencodersCode1
On Large Language Model Continual UnlearningCode1
Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task ArithmeticCode1
General and Task-Oriented Video SegmentationCode1
A Concept-Based Explainability Framework for Large Multimodal ModelsCode1
DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-DomainCode1
Multi-Aspect Controllable Text Generation with Disentangled Counterfactual AugmentationCode1
Sparse Expansion and Neuronal DisentanglementCode1
Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse InputsCode1
Purify Unlearnable Examples via Rate-Constrained Variational AutoencodersCode1
Causal Diffusion Autoencoders: Toward Counterfactual Generation via Diffusion Probabilistic ModelsCode1
3D Face Modeling via Weakly-supervised Disentanglement Network joint Identity-consistency PriorCode1
Cooperative Sentiment Agents for Multimodal Sentiment AnalysisCode1
Disentangling ID and Modality Effects for Session-based RecommendationCode1
Tripod: Three Complementary Inductive Biases for Disentangled Representation LearningCode1
U-VAP: User-specified Visual Appearance Personalization via Decoupled Self AugmentationCode1
Non-negative Contrastive LearningCode1
SF(DA)^2: Source-free Domain Adaptation Through the Lens of Data AugmentationCode1
MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal FusionCode1
Show:102550
← PrevPage 4 of 75Next →

No leaderboard results yet.