Search papers, labs, and topics across Lattice.
4
0
6
3
ILLUME-X achieves unprecedented quality in free-form interleaved text-image generation, setting a new benchmark for multimodal models.
ShotCrop$^3$ transforms a single image into a powerful narrative tool by generating three distinct shots, outperforming existing models in shot localization accuracy.
Ditching the always-on LLM for proactive agents can boost speed by up to 83x and improve F1 scores by 16.7, simply by processing structured event data directly with a temporal graph learning model.
Forget expensive human feedback loops: a VLM-powered reward function can efficiently align image editing diffusion models with human preferences.
