Search papers, labs, and topics across Lattice.
4
1
6
2
LingBot-Video bridges the gap between digital creativity and physical actuation, achieving unprecedented efficiency in video pretraining for embodied intelligence.
LingBot-VLA 2.0 showcases a remarkable leap in robotic manipulation, achieving strong cross-embodiment performance with enhanced predictive capabilities.
Boundary-centric pretraining can dramatically enhance depth estimation, a critical capability for embodied AI systems.
Current robot learning benchmarks may be too simplistic: GM-100 offers 100 new, challenging tasks designed to expose the long-tail behaviors that existing benchmarks miss.
