Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University, Shanghai Innovation Institute, ByteDance Seed ‡ Project lead
2
0
3
Modular TTT reveals that the right combination of learning rate and weight decay can significantly boost performance, while deeper architectures may actually degrade results.
Achieve high-fidelity transparent text animations from image-to-video models without retraining the VAE, sidestepping data scarcity and latent pattern mixing issues.
