Search papers, labs, and topics across Lattice.
7
0
8
1
Exploiting temporal coherence allows for a dramatic reduction in noise and a fivefold increase in inference efficiency for weakly supervised segmentation.
Robots can learn new skills from just one video in under 30 seconds while retaining what they've already mastered鈥攖ransforming the landscape of robotic skill acquisition.
DMuon slashes training time for large models, achieving up to 163x faster optimizer steps while maintaining the benefits of matrix-aware updates.
A single generalist model outperforms specialized systems, achieving over 35% improvement in real-world robotic task success.
SpatialClaw enables agents to dynamically compose and adapt their reasoning strategies, achieving a remarkable 11.2-point accuracy boost over traditional spatial agents.
VLMs trained on the new 4DP-QA dataset show marked improvements in understanding complex 4D scenes, revealing the critical role of disentangling motion dynamics.
By redefining action learning around semantic events, WALL-WM achieves unprecedented generalization across tasks and environments, outperforming traditional models.
