Live intelligence

Latest AI updates

2 updates
Research

EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming

EgoX is an egocentric cross-embodiment learning framework designed to combine demonstrations from humans, real robots, and simulated agents despite differences in morphology, sensing, and control. It pretrains a Modularized Cross-Embodiment Transformer with Embodiment Dreaming (MXT+) using modality-specific tokenizers and action experts over a shared Transformer trunk, then fine-tunes on target-embodiment demonstrations. A training-only dreaming objective predicts latent future visual and proprioceptive states. Across 13 task-embodiment pairs spanning five tasks and six embodiments, cross-embodiment pretraining raised average normalized task progress from 0.63 to 0.80, and from 0.53 to 0.77 under out-of-distribution conditions.

EgoXcross-embodiment learningrobot manipulation
Research

SALA Aligns Latent Actions Across Human and Robot Video for Embodied Foundation Models

SALA introduces semantically aligned latent actions to improve cross-embodiment learning for embodied foundation models. Without paired data, it uses language descriptions of unpaired human and robot clips to estimate semantic similarities and supervise correspondence between human and robot latent actions. Soft neighborhood structures guide human latent actions toward semantically related robot latents, while robot action reconstruction grounds the shared latent space in control. The method claims dual-axis scaling: more general human video for pre-training reduces robot action prediction error, and more task-specific human video for post-training improves real-world robot task success rates.

embodied foundation modelslatent action modelscross-embodiment learning