Search papers, labs, and topics across Lattice.
Princeton University
3
0
7
WorldTrace redefines memory management in video world models, achieving up to 19.5% better episodic recall without any retraining.
Even top-performing video models struggle to identify critical high-risk actions in police body-worn camera footage, highlighting a significant gap in current AI capabilities.
CoMet reveals that decomposing uncertainty into context and multiplicity components can lead to substantial improvements in uncertainty estimation for multimodal AI systems.
