Search papers, labs, and topics across Lattice.
3
0
5
4
Visual fidelity in World Models can be misleading; a model that looks better may perform worse in action robustness, challenging existing evaluation paradigms.
World models may be fundamentally misinterpreting future states, imagining them kinematically rather than dynamically, leading to significant long-horizon failures.
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.
