VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
Shengyu Si, Yuanzhuo Lu, Ruimeng Yang, Ziyi Ye, Zuxuan Wu, Yu-Gang Jiang
THE PROBLEM
This paper focuses on Modern Robot LearningVision-Language-Action model (VLA)A model that takes images and language as input and outputs robot actions.. VLA-Pro lets you dramatically improve robotic Manipulation & TasksManipulationUsing a robot arm or hand to move or interact with objects. Modern Robot LearningGeneralizationThe robot’s ability to work in new situations it has not seen before. by storing task-specific memory adapters during Robot LearningTrainingThe process of fitting a model using data or experience. and retrieving the most relevant ones at test time—boosting real-world success from 5.8% to 65% on unseen tasks. Instead of retraining a full model for new tasks, you dynamically blend learned procedural memories to handle novel object/scene/Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. combinations. Read the paper by tracking the Core ConceptsTaskThe job the robot is supposed to complete, such as pick-and-place, navigation, or drawer opening. definition, the Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. or data assumptions, and the evidence that supports the claimed improvement.
HOW IT WORKS
Task framing
Core method
Data and supervision
Evaluation evidence
KEY RESULTS
VLA-Pro lets you dramatically improve robotic Manipulation & TasksManipulationUsing a robot arm or hand to move or interact with objects. Modern Robot LearningGeneralizationThe robot’s ability to work in new situations it has not seen before. by storing task-specific memory adapters during Robot LearningTrainingThe process of fitting a model using data or experience. and retrieving the most relevant ones at test time—boosting real-world success from 5.8% to 65% on unseen tasks. Instead of retraining a full model for new tasks, you dynamically blend learned procedural memories to handle novel object/scene/Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. combinations.
WHY DEVELOPERS SHOULD CARE
VLA-Pro lets you dramatically improve robotic Manipulation & TasksManipulationUsing a robot arm or hand to move or interact with objects. Modern Robot LearningGeneralizationThe robot’s ability to work in new situations it has not seen before. by storing task-specific memory adapters during Robot LearningTrainingThe process of fitting a model using data or experience. and retrieving the most relevant ones at test time—boosting real-world success from 5.8% to 65% on unseen tasks. Instead of retraining a full model for new tasks, you dynamically blend learned procedural memories to handle novel object/scene/Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. combinations.
LIMITATIONS
The main limitation to check is whether the claimed behavior holds outside the paper's reported setup. That means testing across different Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. embodiments, scenes, objects, and data distributions.
WHAT COMES NEXT
The practical next step is independent reproduction with clear baselines, ablations, and stress tests. For a developer, the useful follow-up is to map the paper's Modern Robot LearningVision-Language-Action model (VLA)A model that takes images and language as input and outputs robot actions. assumptions onto a concrete Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. stack, then test the smallest version of the method that could run end to end.