Training VLAs to perform embodied chain-of-thought reasoning about plans, sub-tasks, motions, and grounded visual features before acting raises OpenVLA success rates by 28% on challenging generalization tasks without new robot data.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
DPO derives the optimal policy directly from human preferences via a reparameterized reward model, solving the RLHF objective with only a binary classification loss and no sampling or separate reward model.
citing papers explorer
-
Robotic Control via Embodied Chain-of-Thought Reasoning
Training VLAs to perform embodied chain-of-thought reasoning about plans, sub-tasks, motions, and grounded visual features before acting raises OpenVLA success rates by 28% on challenging generalization tasks without new robot data.
-
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
DPO derives the optimal policy directly from human preferences via a reparameterized reward model, solving the RLHF objective with only a binary classification loss and no sampling or separate reward model.