Search papers, labs, and topics across Lattice.
2
0
4
58
Unlock zero-shot 3D scene understanding: Ilov3Splat lets you identify and segment arbitrary objects in 3D scenes using only natural language, no category supervision needed.
Forget dataset-specific fine-tuning: a Transformer trained on synthetic data can unlock zero-shot generalized category discovery across vision, text, audio, and remote sensing modalities.
