Search papers, labs, and topics across Lattice.
Affiliation:
3
0
7
An 8x token reduction and 11.1x latency improvement in video generation is achieved by training autoencoders that are generation-aware, not just reconstruction-aware.
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.
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.
