AI Dataset2026
Provides continuous human whole-body manipulation demonstrations for robot policy training, including locomotion and coordinated two-hand actions. Motion is reconstructed from egocentric observations, with reported whole-body joint error of about 3 cm.
Connects scene understanding, long-horizon visual planning, and robot control by alternating language reasoning with video prediction. An agentic variant learns when generated visual evidence is worth using.
Simulates closed-loop interactions between people and wearable AI assistants to test whether multimodal models can guide real-world tasks. Its 120 multi-turn benchmark tasks are scored against verifiable simulator states.
Rewinds world-model trajectories to test alternative robot actions and turn outcome comparisons into action-level training signals. Real-robot data continually corrects the model; across three physical tasks, success rates beat the strongest baseline by 10.67–11.85 percentage points.