Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
This work introduces RoboReel: a unified benchmark for evaluating models that learn policies from human videos, and develops four test suites to evaluate the models' performance on multiple axes, including the robustness to visual distractors and the ability to complete long-horizon tasks.
VLMs struggle with spatial reasoning, but a clever decomposition into sub-problems and probabilistic recombination unlocks significantly better metric-semantic grounding.
