Search papers, labs, and topics across Lattice.
4
0
6
Human trajectory logs are no longer the performance ceiling for autonomous driving: closed-loop reinforcement learning paired with distilled foundation models outperforms human demonstration baselines across major open and closed-loop benchmarks.
Latent reasoning can beat explicit Chain-of-Thought – but only if you force it to learn causal dynamics via a visual world model, not just language.
Autonomous driving models can learn to avoid accidents *before* they happen by training on expert interventions and anticipating errors.
By decoupling generation and refinement experts within a masked diffusion VLA model, DriveFine achieves both flexible decoding and self-correction for autonomous driving.
