Skip to content
conftrace_

concept disentanglement

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

diffusion model (3) text-to-image generation (3) personalized generation (2) feature structuralization (1) compositional interpretability (1) residual token optimization (1) concept fidelity (1) fine-grained domain generalization (1) earth mover's distance (1) attention calibration (1)

Papers

ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization CVPR 2026 Fine-Grained Generalization via Structuralizing Concept and Feature Space into Commonality, Specificity and Confounding AAAI 2026 Intrinsic Concept Extraction Based on Compositional Interpretability CVPR 2026 Attention Calibration for Disentangled Text-to-Image Personalization CVPR 2024 Learning Attention As Disentangler for Compositional Zero-Shot Learning CVPR 2023 DISSECT: Disentangled Simultaneous Explanations via Concept Traversals ICLR 2022