Search papers, labs, and topics across Lattice.
3
0
7
0
Lightweight MLLMs can punch far above their weight in GUI automation when given the right training diet and a little help from their friends.
Achieve superior 3D scene reconstruction from aerial images with significantly reduced transmission overhead by directly optimizing communication for rendering quality.
Stop naively aggregating knowledge for KB-VQA: MaS-VQA's Mask-and-Select mechanism shows how to prune irrelevant image regions and knowledge fragments for better reasoning.
