Newest papers

Post-hoc Epistemic Uncertainty for Vision-Language-Action Policies

Johannes Keller, Albrecht Bloße, Adrian Lindenmeyer, Thomas Neumuth, Daniel Schneider · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29730 · cited by 0 works (OpenAlex) · open-access PDF

Korean

VISION-LANGUE-ACTION (VLA) 정책은 새로운 상황에서 유용한 증거 또는 도움을 요청하기 위해 훈련 지식의 격차를 인식해야합니다, 특히 실패가 비용이 많이 들 때. 독립적으로 훈련 된 정책의 집합 내에서 불일치가 이러한 결정을 안내 할 수 있지만 교육 및 여러 정책을 실행하는 것이 필요합니다. 우리는 단일 정책의 삽입에서 에피스메틱 불확실성을 추정하는 포스트 호크 코어 변수 머리를 제안합니다. 각 머리는 훈련 데모의 삽입에서 삽입을 조건화 한 Gaussian 프로세스의 조건적 변수를 계산합니다. 삽입은 회귀 목표 또는 gradient 업데이트를 필요로하지 않으며 SmolVLA에 대한 실험에서 LIBERO-10에 대한 정책을

Machine translation (Meta M2M100); the English original follows.

Abstract

Vision-language-action (VLA) policies need to recognize gaps in their training knowledge to request useful demonstrations or assistance in new situations, especially when failures are costly. Disagreement within an ensemble of independently trained policies can guide these decisions, but requires training and running multiple policies. We propose post-hoc kernel-variance heads that estimate epistemic uncertainty from the embeddings of a single policy. Each head computes the conditional variance of a Gaussian process conditioned on embeddings from the training demonstrations. Fitting requires no regression targets or gradient updates and leaves the policy unchanged. In experiments with SmolVLA on LIBERO-10, the kernel variance heads perform competitively with two-policy ensemble scores in task-level correlation with task success, in demonstration acquisition during active learning, and in referral to a stronger supervisor policy as a proxy for human assistance. For SmolVLA, the head on the vision-language backbone reduces uncertainty-scoring time by up to approximately a factor of 50 compared with ensemble scores, while also substantially reducing setup costs. We also show that the established evaluation protocol on LIBERO-10 primarily rewards recognition of coverage differences between tasks, while execution variability weakens assessment of within-task rankings. Thus, controlled perturbations provide a complementary evaluation: modality-specific heads identify unfamiliar camera, instruction, or state inputs, while fused heads can detect unfamiliar combinations of individually familiar inputs. With a supervisor proxy trained on the evaluated perturbation families, the decoder head improves within-task referral over ensemble disagreement. These findings show that useful uncertainty estimates for adaptive robot learning can be obtained from a single policy.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Supervisor, Computer science, Variance (accounting), Artificial intelligence, Proxy (statistics), Machine learning

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange