Embodied AI

Trajectory Diffusion (T-Diff) significantly improves object goal navigation by learning sequential planning through trajectory diffusion, resulting in more accurate and efficient navigation.

SG-Nav achieves state-of-the-art zero-shot object navigation by leveraging a novel 3D scene graph to provide rich context for LLM-based reasoning.

MO-DDN: A new benchmark and coarse-to-fine exploration agent boosts embodied AI’s ability to handle multi-object, preference-based task planning.

Researchers unveil unified architecture for grounding multimodal large language models in actions, showing superior performance with learned tokenization for continuous actions and semantic alignment …

GenRL: Learn diverse embodied tasks from vision & language, without reward design, using multimodal imagination!

ExRAP: A novel framework boosts embodied AI’s continual instruction following by cleverly combining environment exploration with LLM-based planning, leading to significantly improved task success and …

ARCHITECT: Generating realistic 3D scenes using hierarchical 2D inpainting!

Any2Policy: a unified multi-modal system enabling robots to perform tasks using diverse instruction and observation modalities (text, image, audio, video, point cloud).