Search papers, labs, and topics across Lattice.
Drive. We further evaluate zero-shot transfer from real-world logs to simulation on Bench
7
0
5
UNIVERSE achieves a remarkable 4.3× speedup in trajectory inference while maintaining planning accuracy, revolutionizing how video dynamics inform autonomous driving actions.
SWAM achieves superior navigation performance by seamlessly integrating observation and action generation, significantly enhancing efficiency and accuracy in embodied tasks.
Discrete-WAM enables compositional causal reasoning in autonomous driving, outperforming traditional methods that struggle with complex state-action dynamics.
Ditch pixel-perfect reconstruction: LVDrive shows that learning future scene representations in a high-level latent space dramatically improves autonomous driving performance.
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 now achieve remarkable zero-shot generalization by leveraging the power of large-scale video generation models to jointly predict future actions and visuals.
Autonomous driving models no longer need to compromise between spatial perception and semantic reasoning: UniDriveVLA's expert decoupling unlocks state-of-the-art performance across a range of driving tasks.
