Search papers, labs, and topics across Lattice.
4
5
6
Achieve 20x faster motion capture for arbitrary skeletons with a new end-to-end framework that cuts rotation error nearly in half.
A unified benchmark reveals the trade-offs between pixel-wise accuracy and perceptual realism in state-of-the-art image super-resolution techniques.
Achieve significantly better vocal-to-accompaniment generation by reformulating it as a discrete masked diffusion process, finally balancing acoustic fidelity, coherence, and orchestration.
Human-like evaluation of long-form generative AI is now possible, thanks to a new framework that breaks down reference answers into weighted, context-aware scoring points.
