Metraipolis › archive › dc_38ec26b976bf

ValueFormer: Stage-Aware Value Labels for Online Failure Detection and VLA Post-Training — arXiv:2608.02958

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.02958
License (as archived)
CC0-1.0
Archived
2026-10-31T12:18:24.080Z
SHA-256 of the archived text
1597713053ae3054656fadb9edfde42a837e0a9eb2b133b045c69ea532f51f0e
Stable URL of this page
https://metraipolis.com/documento/dc_38ec26b976bf

How to cite

ValueFormer: Stage-Aware Value Labels for Online Failure Detection and VLA Post-Training — arXiv:2608.02958 — arXiv (en), https://arxiv.org/abs/2608.02958 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_38ec26b976bf (Metraipolis archive dc_38ec26b976bf, sha256 1597713053ae3054656fadb9edfde42a837e0a9eb2b133b045c69ea532f51f0e)
BibTeX
@misc{dc38ec26b976bf,
  title = {ValueFormer: Stage-Aware Value Labels for Online Failure Detection and VLA Post-Training — arXiv:2608.02958},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.02958},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_38ec26b976bf; sha256 1597713053ae3054656fadb9edfde42a837e0a9eb2b133b045c69ea532f51f0e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02958. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generalist vision-language-action (VLA) policies now transfer to new scenes with little task-specific training, but they still fail silently: from the action stream alone, a collapsing rollout looks much like one making clean progress, because imitation supplies no notion of progress. The cheap alternative, a terminal success / failure bit, is learnable in principle yet too sparse to say when a rollout went wrong. We argue that the per-frame label is the hard part, and that it works better when continuous and non-monotonic: a score rather than a single success or failure, and one free to fall and then rise again as a rollout goes wrong and recovers. Such a label is cheap to obtain: a person marks only the stage at which an episode went wrong, and the per-frame values are computed from that. We present ValueFormer, a policy-agnostic causal transformer (3.5M parameters) over a frozen DINOv3 backbone, emitting two per-frame signals in one forward pass: a smooth Monte Carlo value for advantage estimation and a sharp binary value for online mistake detection. Failed episodes carry a stage-aware, success-then-decay return. A teleoperation station already records an intervention flag; reusing it lifts held-out detection from 0.38 to 0.82 average precision and flags 95% of mistakes before the operator reacts. On a real bimanual sandwich station, feeding the critic back as a per-frame post-training weight raises task completion from 70% to 85% and removes a repeat-pick failure mode in our trials, although at n=20 that gain sits within noise.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.02958 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:05:52.969Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).