Verifier-free Test-Time Sampling for Vision Language Action Models
This addresses precision limitations in robot control tasks, offering a verifier-free method that generalizes better than prior approaches, though it is incremental as it builds on test-time scaling ideas.
The paper tackles the problem of improving precision in Vision-Language-Action models for robot control by proposing MG-Select, a test-time scaling framework that uses internal model properties without external verifiers, achieving a 28%/35% improvement in real-world in-distribution/out-of-distribution tasks and a 168% relative gain on RoboCasa pick-and-place tasks.
Vision-Language-Action models (VLAs) have demonstrated remarkable performance in robot control. However, they remain fundamentally limited in tasks that require high precision due to their single-inference paradigm. While test-time scaling approaches using external verifiers have shown promise, they require additional training and fail to generalize to unseen conditions. We propose Masking Distribution Guided Selection (MG-Select), a novel test-time scaling framework for VLAs that leverages the model's internal properties without requiring additional training or external modules. Our approach utilizes KL divergence from a reference action token distribution as a confidence metric for selecting the optimal action from multiple candidates. We introduce a reference distribution generated by the same VLA but with randomly masked states and language conditions as inputs, ensuring maximum uncertainty while remaining aligned with the target task distribution. Additionally, we propose a joint training strategy that enables the model to learn both conditional and unconditional distributions by applying dropout to state and language conditions, thereby further improving the quality of the reference distribution. Our experiments demonstrate that MG-Select achieves significant performance improvements, including a 28%/35% improvement in real-world in-distribution/out-of-distribution tasks, along with a 168% relative gain on RoboCasa pick-and-place tasks trained with 30 demonstrations.