VLA Failures Become Corrective Training Signals
RedFlow converts failed robot actions into localized corrections for vision-language-action policy improvement.
Market Driver: data efficiency
Temporal Constraints Target More Stable Latent Actions
The research introduces temporally constrained latent-action learning for more coherent embodied control.
RedFlow Turns Robot Failures Into Action-Level Corrections
The paper proposes converting failed actions into localized corrections for flow-matching vision-language-action policies.
DLAM Adds Temporal Constraints to Latent Robot Actions
DLAM introduces temporal constraints intended to make latent robot actions more coherent across sequential control decisions.
Pegasus converts human video into robot-learnable experience
Pegasus translates human demonstrations into robot-conditioned data using task graphs, affordances, constraints, and physics verification.
