RoboWits benchmark with 238 tasks shows pre-trained VLAs succeed on seed tasks but fail on mutated ones, highlighting brittleness in reasoning.
Tenenbaum, Daniela Rus, and Chuang Gan
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
COSMIC co-optimizes robot structure, materials, and control simultaneously via differentiable simulation and constrained gradients, yielding locomotion strategies that outperform sequential baselines.
citing papers explorer
-
RoboWits: Unexpected Challenges for Robotic Creative Problem Solving
RoboWits benchmark with 238 tasks shows pre-trained VLAs succeed on seed tasks but fail on mutated ones, highlighting brittleness in reasoning.
-
COSMIC: Concurrent Optimization of Structure, Material, and Integrated Control for robotic systems
COSMIC co-optimizes robot structure, materials, and control simultaneously via differentiable simulation and constrained gradients, yielding locomotion strategies that outperform sequential baselines.