Search papers, labs, and topics across Lattice.
2
0
5
2
A reward-compatible bounded mixing mechanism for $\gamma\mathrm{OPD}$ that balances verifiable outcome feedback with the discounted OPD advantage to move beyond purely teacher-dependent optimization is developed.
Achieve real-time autonomous driving policy generation with a new flow-matching RL algorithm that slashes inference latency without sacrificing performance.
