Search papers, labs, and topics across Lattice.
Affiliation:
3
0
2
A training-free framework that reformulates failure recovery as test-time scaling over causal histories, which decomposes recovery into three coupled decisions: when to revise the causal history, where to recover a reliable history prefix, and which history configuration best supports subsequent execution.
Test-time planning for robots can be dramatically improved by focusing on selecting reliable future-action hypotheses rather than merely generating more of them.
Soft robots can learn to infer and manipulate objects through rich physical interactions, achieving effective grasping without direct measurement of key properties.
