Search papers, labs, and topics across Lattice.
3
0
5
CuRe transforms video captioning reward design by shifting from holistic evaluations to precise claim-level verification, significantly boosting factual accuracy and diversity in generated captions.
STARE not only prevents policy entropy collapse but also enhances accuracy by up to 8% across diverse tasks, showcasing a new frontier in stable RL training.
Achieve high-quality 3D style transfer from a single scene by injecting a 2D-pretrained decoder, sidestepping the usual data scarcity bottleneck.