Search papers, labs, and topics across Lattice.
The University of Hong Kong
5
0
6
Closing the real-to-sim gap in continuum dynamics requires modeling subtle material properties beyond simple isotropy – and MoSA shows how to do it.
Achieving robust brain decoding across subjects without any retraining could revolutionize how we interpret neural signals in diverse populations.
Humanoid robots can now recover from extreme perturbations with more natural, human-like movements by using a diffusion model as a learned intermediary between high-level commands and low-level motor control.
Sparse-view 3D Gaussian Splatting gets a major boost by incorporating priors from geometry foundation models and VLMs to overcome the limitations of color residual heuristics.
Humanoid robots can now learn complex, terrain-aware motions directly from video using a low-cost pipeline, eliminating the need for expensive MoCap data and manual motion design.
