Search papers, labs, and topics across Lattice.
3
0
4
3
World in World is presented, a training-free inference-time interface that converts heterogeneous control evidence into camera- and time-labelled clean visual states, which are read through the native self attention of a frozen causal video model.
Achieving superior 3D scene reconstruction from a single measurement, this method combines Gaussian Splatting with advanced vision model priors to tackle the complexities of Snapshot Compressive Imaging.
Ditch the handcrafted coefficients: DyWeight learns how to dynamically weight gradients in diffusion model sampling, slashing compute while boosting image quality.
