Search papers, labs, and topics across Lattice.
2
0
6
Bridging the gap between 3D and 4D point cloud understanding, PointATA unlocks surprisingly strong performance with parameter-efficient transfer learning, even surpassing full fine-tuning.
By learning to intelligently "zoom in" on relevant image regions, TikArt significantly boosts MLLM performance on fine-grained visual reasoning tasks.
