Search papers, labs, and topics across Lattice.
Affiliation:
5
0
6
0
Unsupervisedly uncover and neutralize hidden model misalignments transferred during distillation, even without prior knowledge of the problematic trait.
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.
Preserving spatial topology in quantum many-body simulations can drastically reduce compilation overhead, unlocking new efficiencies in quantum computing.
Explicit multi-timescale predictions in LM-X not only enhance robot manipulation success rates but also provide intrinsic explanations for control decisions, transforming how we understand robotic action generation.
Long-tail semantic failures in document understanding are exposed when models are forced to reason with a unified vocabulary of visual anchors rather than treating elements in isolation.
