Search papers, labs, and topics across Lattice.
5
0
3
16
EgoAfford reveals that effective task-oriented affordance grounding can significantly enhance multi-step planning in complex environments.
Action-aligned 3D tracker features can boost VLA policy performance by over 25 points, revolutionizing how robots learn from demonstrations.
Calibration-free dexterous hand retargeting achieves intuitive control and superior performance without the need for hand-specific tuning.
ChronoFlow-Policy outperforms traditional methods by effectively unifying past and future interaction dynamics, enhancing performance in complex manipulation tasks.
A novel representation for articulated parts perception achieves 73% manipulation success without the need for extensive fine-tuning.
