cs.RONov 17, 2026

RageVLA: Augmentation-Trained Perception and Action for State-of-the-Art Robustness on LIBERO

Authors: Amrit Lal Singh, Smarak Kanjilal

Abstract

Vision-language-action (VLA) models look saturated on LIBERO, yet most of them fall apart on LIBERO-PRO as soon as an object moves or the instruction asks for something new. We argue that what is missing is not scale but decoupling. In these policies, what to do is tied to where things were during training, to the scene around them and to the wording of the instruction. We cut these ties in two places. In the data, LIBERO demonstrations are re-arranged by general rules: every object and fixture is moved and rotated, tasks are carried into other environments and onto other surfaces, and every instruction is paraphrased. In the policy, a perception engine on frozen DINOv3 features, trained on this augmented data, hands the action model the scene in decoupled form: a list of objects with their positions, and a compact code of what the gripper is looking at, next to image and instruction embeddings from TinyCLIP. A flow-matching diffusion transformer, trained from scratch, acts on this view. We call this combination of Robust Augmentation and Grounded Encoding RageVLA. With 0.21 billion parameters, RageVLA sets a new state of the art on LIBERO-PRO among VLA policies, scoring 0.72 against 0.53 for the best published model, and a larger variant reaches 0.73. Two further tests on LIBERO-Object show that the policy acts on what it perceives. When the object positions it is given are shuffled while the camera images stay correct, its success falls from 0.965 to 0.215. When the target object is displaced by 28 cm, it still succeeds in 0.865 of the episodes, where π0.5π_{0.5}, run through the same harness, succeeds in 0.105.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models

    Jun 22, 2026Rongxu Cui, Zongzheng Zhang, Jingrui Pang +11Robot SafetyVision-Language-Action Models

  2. CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model

    Jul 28, 2026Minhyeok Lee, Chiyoung Kim, Chanhoe Gu +5Reasoning for VLAsEfficient VLA Inference