Search papers, labs, and topics across Lattice.
2
0
4
A single 24GB GPU can now perform untiled 4K VSR at 2x DiT speed, thanks to hybrid attention that balances local and global interactions.
Decoupling denoising and context writing parameters in autoregressive video models unlocks unprecedented long-horizon generation capabilities, extending continuous output to 24 hours from just 5-second training rollouts.