R5DGS: Semantic-Aware 4D Gaussian Splatting with Rigid Body Constraints for Efficient Dynamic Scene Reconstruction Paper โข 2605.25909 โข Published May 25
AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models Paper โข 2605.25901 โข Published May 25 โข 1
RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments Paper โข 2604.26067 โข Published Apr 28 โข 77
Green-VLA: Staged Vision-Language-Action Model for Generalist Robots Paper โข 2602.00919 โข Published Jan 31 โข 312