vla-manipulation-policies-doing-single-step-action-prediction-libero-observations CLM-0506observationsingle paperReviewed by AI
For VLA manipulation policies doing single-step action prediction on LIBERO observations, the commanded action is fragile to camera rotation but tolerant of brightness: validated over entire continuous perturbation regions, 27% of instances admit a counterexample within ±1° of camera rotation and 51% within ±2°, while every instance is robust to a ±2% brightness shift and the median tolerates ±30%.
Capability: Turning plans into physical action
Observed on
Five LIBERO-finetuned VLAs (OpenVLA, OpenVLA-OFT, GR00T N1.7, pi0, pi0.5), 40 sampled observations, open-loop one-step action prediction, tolerance set at the 90th percentile of co.
Sources
- Validated by: Compared against uniform random sampling on the 2,835 VLA instances where a counterexample was found: sampling found nothing on 34 within a 17,000-draw budget and was slower from two iterations onward; against the original H2V on 100 robust instances it used 15.3x fewer queries in total and decided all 100 where H2V left 32 undecided. A k-draw sampling protocol wrongly called an instance robust in 50% of its robust reports at k=1, 42% at k=10, 6% at k=100.. [truncated]
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- For vision-language-action and world-action manipulation policies evaluated on LIBERO-style tasks, near-ceiling one-shot task success does not predict the ability to resume a task from a failure state that arose during the model's own execution: all six tested policies lost over half their success rate on recovery scenarios, rankings inverted between the two settings, and recovery success fell steeply as the failure altered object or environment state rather than just the last action.Turning plans into physical action · reviewed by AI
- When VLMs must operate unfamiliar household devices with no manual, through multi-turn interaction over rendered multi-view images with click/rotate actions at pixel coordinates, the limiting failure is fine-grained localization of the interactive component within the correct view rather than navigating to that view, and almost no task is completed in the optimal number of steps.Turning plans into physical action · reviewed by AI
- For VLA and world-action manipulation policies that score near-ceiling on standard LIBERO, recovery success after a real execution failure falls sharply as recovery requires deeper state reasoning \u2014 retrying or adapting the immediate action works far more often than restoring a displaced task object or clearing an environmental obstruction \u2014 and rankings on the standard benchmark do not predict recovery rankings.Turning plans into physical action · reviewed by AI
- When fine-tuning a vision-language-action policy for a deployment shift, the parameter change needed concentrates in the functional region matching the shift's modality — appearance in the vision encoder, rephrased instructions in the language backbone, novel objects in the vision encoder plus action head — so allocating LoRA rank per region by a pre-training diagnostic beats uniform-rank LoRA at matched budget, with the advantage largest at small budgets and absent when the shift's demand spreads across regions rather than concentrating.Turning plans into physical action · reviewed by AI
- For memory-augmented VLA manipulation policies that must actively move the viewpoint to find task-relevant evidence, writing one memory frame at each fixed action-chunk boundary generalizes better than event-triggered writing (on predicted subtask change or on gripper/head/torso motion), and extra memory capacity helps only under the regular schedule — event-triggered policies degrade further out of distribution because mistimed triggers omit informative views and control jitter fills memory with redundant frames.Turning plans into physical action · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: A validation run over the same continuous regions on these or comparable LIBERO-finetuned VLAs showing no action-changing perturbation within ±2° of rotation, or showing brightness failures below ±2%.