Search papers, labs, and topics across Lattice.
Affiliation:
4
0
4
3
TTS achieves a remarkable 74.8% success rate in long-horizon manipulation by grounding high-level goals in real-world observations, transforming how robots learn from human demonstrations.
HERO enables robots to autonomously evolve manipulation skills from scratch, drastically reducing reliance on human demonstrations.
Human-in-the-loop chunk-wise residual adaptation closes the reality gap for dexterous robot manipulation, boosting success rates by up to 43% compared to offline imitation learning.
Human-in-the-loop learning can now boost dexterous manipulation VLA models by 25%, thanks to a new framework that smartly samples corrective actions and enables real-time intervention.
