structural consistency
Structural consistency refers to the degree to which a model's predictions maintain coherent relationships with the underlying data structure, ensuring logical and plausible outputs.
- Bilevel Network Learning via Hierarchically Structured Sparsity
- Coarse-to-Fine 3D Part Assembly via Semantic Super-Parts and Symmetry-Aware Pose Estimation
- DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editing
- Enhancing Consistency of Flow-Based Image Editing through Kalman Control
- GeoVideo: Introducing Geometric Regularization into Video Generation Model
- GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments
- Learning Repetition-Invariant Representations for Polymer Informatics
- Negative Feedback Really Matters: Signed Dual-Channel Graph Contrastive Learning Framework for Recommendation
- ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search
- QSCA: Quantization with Self-Compensating Auxiliary for Monocular Depth Estimation
- RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation
- SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction
- Video Perception Models for 3D Scene Synthesis
- WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception
- Zero-Shot Blind-Spot Image Denoising via Cross-Scale Non-Local Pixel Refilling