spatial relationships
Understanding and modeling the relationships between objects in space, often crucial in tasks related to image processing and computer vision, where the arrangement of elements affects interpretations.
- Accurate KV Cache Eviction via Anchor Direction Projection for Efficient LLM Inference
- CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects
- GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization
- MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation
- Object-centric binding in Contrastive Language-Image Pretraining
- PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
- PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning
- Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
- Role-aware Multi-agent Reinforcement Learning for Coordinated Emergency Traffic Control
- SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation
- ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference
- Spatially-aware Weights Tokenization for NeRF-Language Models
- Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
- Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes