Search papers, labs, and topics across Lattice.
3
0
5
High-fidelity, feed-forward 3D editing no longer requires paired 3D training data or agonizing test-time optimization: regularizing 2D visual and VLM distillation with a 3D latent distribution matching objective is enough to prevent geometric collapse.
Achieving high visual fidelity while ensuring physical consistency in video generation could redefine the standards for simulating realistic interactions in AI-generated content.
AOHP redefines how AI agents interact with operating systems, achieving a 21% boost in task completion and a dramatic cut in execution costs.
