Search papers, labs, and topics across Lattice.
3
0
6
2
Instead of trusting black-box scalar scores to evaluate world models, video verification can match end-to-end VLM recall while producing fully auditable, spatiotemporally grounded physical proofs of failure.
LDR achieves unprecedented extrapolation of learned dynamics in video models, outperforming traditional methods by a staggering margin in both accuracy and efficiency.
Chimera achieves 7.3x compute efficiency over traditional models while enabling zero-shot extrapolation from short video clips to significantly longer sequences.
