Latest

• CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
• Multiview Scene Graph
• VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model
• ActFormer: Scalable Collaborative Perception via Active Queries
• LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images
• Tell Me Where You Are: Multimodal LLMs Meet Place Recognition
• Multi-Robot Scene Completion: Towards Task-Agnostic Collaborative Perception