Similar Items: DCR: Counterfactual Attractor Guidance for Rare Compositional Generation
- Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
- Representation Fréchet Loss for Visual Generation
- GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
- Identity-Consistent Multi-Pose Generation of Contactless Fingerprints
- Large Language Models are Universal Reasoners for Visual Generation
- Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs