Search papers, labs, and topics across Lattice.
Singapore University of Technology
2
0
4
A novel decoupled autoencoder design unlocks 32x spatial compression for diffusion models while simultaneously boosting reconstruction fidelity and accelerating training convergence.
Unsupervised visual tracking gets a surprising boost from text-to-image diffusion models, which can be prompted to highlight the target object in each frame without any training data.
