Search papers, labs, and topics across Lattice.
3
52
5
10
A single 500-hour visual-tactile dataset boosts zero-shot contact prediction from 13% to 38% IoU and quadruples robot manipulation success rates, proving scale and consistency are paramount for embodied learning.
Controllable 3D generation takes a leap forward with 3D-ReGen, a framework that leverages an initial 3D shape for tasks like enhancement and editing, outperforming existing methods.
Unlock human-like spatial reasoning in VLMs with VLM-3R, which reconstructs 3D understanding from monocular video using instruction tuning, bypassing the need for external depth sensors.
