Search papers, labs, and topics across Lattice.
5
0
5
4
SGF transforms autoregressive video generation by enabling effective long-video extrapolation from just a 5-second training window.
OmniDirector achieves unprecedented control over camera motion in video generation, enabling director-level precision without relying on scarce cross-paired data.
Diffusion models can now handle arbitrary, unordered sparse inputs for 3D reconstruction, achieving robust and scalable performance across irregular viewpoints and long trajectories.
Overcome data sparsity in sequential recommendation with a new framework that learns fine-grained user preferences from diverse behaviors, leading to state-of-the-art performance.
Generate multi-shot videos at 16 FPS with a single GPU and interactively steer the narrative in real-time, thanks to a novel causal architecture that overcomes the limitations of bidirectional models.
