Similar Items: BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation
- HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion Models
- Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment
- Representation Fréchet Loss for Visual Generation
- Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements
- Learning Coarse-to-Fine Osteoarthritis Representations under Noisy Hierarchical Labels
- Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenizatio