Search papers, labs, and topics across Lattice.
2
0
4
Achieve significant speedups in diffusion model inference, without training, by adaptively selecting the best predictor for each token at each step based on a low-cost probe of the first layer.
Autoregressive video models can now generate 4-minute videos without retraining, thanks to a clever inference-time hack that fixes positional embedding bias and injects dynamic priors.
