iMaC: Translating Actions into Motion and Contact Images for Embodied World Models Paper • 2606.09813 • Published 22 days ago • 13
Running on Zero Agents 68 Yoloe 🚀 68 Detect and segment objects in images using text, visual, or prompt-free prompts
Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding Paper • 2502.10392 • Published Feb 14, 2025 • 6
EmbodiedSAM: Online Segment Any 3D Thing in Real Time Paper • 2408.11811 • Published Aug 21, 2024