AI & ML
RageVLA: Augmentation-Trained Perception and Action for State-of-the-Art Robustness on LIBERO
arXiv cs.RO0 views
arXiv:2611.23517v1 Announce Type: new 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 $\pi_{0.5}$, run through the same harness, succeeds in 0.105.
Source:https://arxiv.org/abs/2611.23517PreviousLearning and Control in Physically Coupled Dynamical SystemsNextRESCUE Jumper: A Centimeter-Scale Rolling and Jumping Robot for Search and Rescue
Related posts
How OpenAI’s Performance Factory keeps ChatGPT fast
0OpenAI Blog
Meta’s AI agent Muse is mixing up conversations and exposing private data, report says
0TechCrunch
Google gives Gemini the ability to use your Mac for you
0TechCrunch
Linkup /research is async. Treating it as synchronous is the bug, in code and in the freeze case
0dev.to
Fuck Your AI Safeguards
0Hacker News
Chrome AI features wasting much bandwidth
0Hacker News