Search papers, labs, and topics across Lattice.
3
0
4
Tactile-reactive manipulation can boost robotic success rates by over 30% in delicate tasks, revolutionizing how robots interact with their environment.
Stateful Visual Encoders enable VLMs to leverage prior visual context, leading to substantial performance gains in multi-image tasks.
Achieve globally consistent 3D reconstruction over sequences exceeding 19,000 frames by combining test-time training with sliding window attention, outperforming prior state-of-the-art methods by over 74% on ATE on KITTI.
