Search papers, labs, and topics across Lattice.
4
0
6
0
Over 1,500 submissions revealed stark differences in model performance across diverse domains, highlighting the challenges of generalizing egocentric video understanding.
FashionAM revolutionizes fashion image retrieval by directly linking multimodal queries to visual embeddings, eliminating the pitfalls of textification.
Achieving an 80.9% success rate in spatial reasoning tasks, RoboSpatialBrain reveals the critical role of selective reasoning activation in embodied AI.
FashionLens achieves state-of-the-art performance in versatile fashion image retrieval by dynamically adapting query representations to task-aligned metric spaces, outperforming specialized models.
