Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
0
Joint audio-video diffusion models hallucinate not from diffuse attention noise, but because bidirectional audio-video cross-attention systematically overrides text conditioning in favor of learned canonical priors.
HairPort achieves accurate hairstyle transfers even under extreme pose and scale variations, setting a new standard for identity-preserving image synthesis.
