RePO-VLA raises average adversarial success rates in VLA manipulation from 20% to 75% by using recovery-aware initialization, a progress-aware semantic value function, and value-conditioned refinement on success and corrective trajectories.
Thriftydagger: Budget-aware novelty and risk gating for interactive imitation learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.RO 4roles
background 2polarities
background 2representative citing papers
A verifier called Future Forward Dynamics Causal Attention enables adaptive action execution in World Action Models, reducing model inferences by 69% and improving success rates in robotic tasks.
TER-DAgger improves robotic precision insertion success rates by over 37% via residual policies from edited trajectories and force-aware intervention triggers.
MimicGen creates over 50K robot demonstrations from roughly 200 human ones, allowing imitation learning to achieve strong performance on complex long-horizon tasks like assembly and coffee preparation.
citing papers explorer
-
RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models
RePO-VLA raises average adversarial success rates in VLA manipulation from 20% to 75% by using recovery-aware initialization, a progress-aware semantic value function, and value-conditioned refinement on success and corrective trajectories.
-
When to Trust Imagination: Adaptive Action Execution for World Action Models
A verifier called Future Forward Dynamics Causal Attention enables adaptive action execution in World Action Models, reducing model inferences by 69% and improving success rates in robotic tasks.
-
Force-Aware Residual DAgger via Trajectory Editing for Precision Insertion with Impedance Control
TER-DAgger improves robotic precision insertion success rates by over 37% via residual policies from edited trajectories and force-aware intervention triggers.