Search papers, labs, and topics across Lattice.
4
0
6
11
Visual fidelity in World Models can be misleading; a model that looks better may perform worse in action robustness, challenging existing evaluation paradigms.
Even state-of-the-art VLMs stumble when reasoning about sequential driving scenes, achieving only 57% accuracy compared to human-level 65%, exposing critical gaps in understanding vehicle dynamics and temporal relations.
A 4B-parameter model outperforms Gemini-3-Pro in autonomous driving by incorporating physics-informed constraints and style-aware training, suggesting specialized models can surpass larger, general-purpose models in domain-specific tasks.
By learning where to sample, autonomous vehicles can achieve up to 84% faster motion planning in complex urban environments without sacrificing safety or success rates.
