Search papers, labs, and topics across Lattice.
2
0
3
REARL, a closed-loop simulation enhancement framework that integrates real traffic data with large language model (LLM) and modulates the simulated vehicle with reference to that real action, is proposed.
BETA achieves state-of-the-art continual learning performance with just 0.05 million trainable parameters, outperforming traditional methods by 180–3000 times in parameter efficiency.
