structural fidelity
The degree to which a model preserves the underlying structure of the data during learning and inference, particularly important in graph-based or relational data.
- DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
- Generative Modeling of Full-Atom Protein Conformations using Latent Diffusion on Graph Embeddings
- Hypergraph-Enhanced Contrastive Learning for Multi-View Clustering with Hyper-Laplacian Regularization
- SSIMBaD: Sigma Scaling with SSIM-Guided Balanced Diffusion for AnimeFace Colorization
- Spectral Graph Coarsening Using Inner Product Preservation and the Grassmann Manifold
- Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders
- Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization