Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
3
AVA-Encoder achieves a 73.1% relative improvement in video representation learning, enabling agents to produce cinematic-grade videos with far fewer resources.
Naive matching in diffusion distillation can inadvertently amplify errors due to hidden information in teacher models, leading to a surprising failure mode called Negative Branch Asymmetry.
