Search papers, labs, and topics across Lattice.
Affiliation:
2
1
6
6
This work introduces physical rank consistency (PRC) to measure how well tokenization preserves local physical distance rankings after reconstruction, and presents ActionPiece, which preserves physical action relationships through joint supervision of representation learning and quantization.
SIEVE reveals that leveraging reusable structures in demonstration data can lead to more efficient and effective imitation learning, outperforming full-data training with significantly less input.
