Search papers, labs, and topics across Lattice.
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University;
3
0
4
6
FTP-1 not only excels on familiar tactile sensors but also achieves unprecedented success on unseen setups, redefining the potential for cross-sensor generalization in robotic manipulation.
By explicitly modeling signal processing constraints, ZoomSpec achieves state-of-the-art wideband spectrum sensing, outperforming existing deep learning methods that treat spectrograms as natural images.
Visual grounding in VLAs weakens in deeper layers, but injecting multi-level visual features and pruning irrelevant tokens can boost performance by 9% in simulation and 7.5% in the real world.
