Search papers, labs, and topics across Lattice.
Affiliation:
6
0
9
27
HAF outperforms conventional VLA models in humanoid loco-manipulation by effectively managing complex motion coordination without the need for extensive computational resources.
Current state-of-the-art world models struggle to maintain spatial consistency and reliable state evolution over long-horizon interactions, as revealed by the new PlayWorld benchmark.
Grounding EEG interpretations in hardware capabilities can drastically reduce unsupported conclusions and improve the reliability of scientific software.
Sparse queries offer a surprisingly effective and efficient alternative to dense representations for image-to-3D generation, achieving comparable fidelity with less input-view bias.
Achieve real-time 360° robotic vision with RobotPan, which drastically reduces the number of Gaussians needed for reconstruction and view synthesis compared to previous feed-forward methods.
Achieve human-like dexterity in humanoid robots by unifying visual-language cues with learned whole-body proprioceptive dynamics, outperforming prior methods in complex manipulation tasks.
