Search papers, labs, and topics across Lattice.
M utterances from 6,000+ speakers spanning a wide range of ethnicities, accents, and recording conditions; we use a
4
0
5
Lip Forcing achieves real-time lip synchronization at unprecedented speeds, outperforming traditional models by over 39 times while maintaining high fidelity.
By treating camera pose as a unifying geometric representation, WorldCam achieves significantly improved action controllability and long-horizon 3D consistency in interactive gaming world models compared to prior video diffusion transformer approaches.
Imagine a world model that doesn't just dream up environments, but flawlessly renders a real city like Seoul, complete with text-prompted scenarios and diverse camera movements.
By explicitly aligning attention with external correspondences, CORAL significantly improves detail preservation in virtual try-on, addressing a key limitation of existing Diffusion Transformer methods.
