Search papers, labs, and topics across Lattice.
4
0
6
REST achieves few-step image generation that rivals traditional 40-step methods while slashing training costs by over 75%.
Unifying motion and camera controls in a single visual representation leads to unprecedented improvements in video generation fidelity and robustness.
Models may ace aesthetics but falter on geometry鈥擲VGEval reveals the critical gaps in text-to-SVG generation evaluation.
Transforming video generation from a pixel sampling problem to a structured orchestration of the physical world, WNM enables unprecedented control and efficiency in content creation.
