Search papers, labs, and topics across Lattice.
2
0
5
Robots can adapt to unseen tasks purely through simulated imagination, boosting real-world manipulation success from 20% to 77% without requiring new human demonstrations or external environment rollouts.
Overcoming the 2D-to-4D spatial bottleneck in VLMs does not require native 3D architectures; factorizing visual projections into verifiable planar, depth, and temporal RL objectives delivers immediate 4-6% benchmark gains.
