Search papers, labs, and topics across Lattice.
3
0
6
Quality-aware pretraining strategies, particularly approach-aware episode conditioning, can significantly outperform plain behavioral cloning in VLA tasks, with optimal choices depending on label granularity and model architecture.
A single set of learned manipulation skills transfers to the real world with 78% success, bypassing the need for task-specific fine-tuning or re-training on real data.
