Metraipolis › archive › dc_e780ba7557b7

NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models — arXiv:2610.23271

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23271
License (as archived)
CC0-1.0
Archived
2026-10-19T09:21:23.778Z
SHA-256 of the archived text
35a5f64dec1adc110e5cd786177d2c22eca0c6c923a51b5d30f149dbf4f91ad6
Stable URL of this page
https://metraipolis.com/documento/dc_e780ba7557b7

How to cite

NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models — arXiv:2610.23271 — arXiv (en), https://arxiv.org/abs/2610.23271 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e780ba7557b7 (Metraipolis archive dc_e780ba7557b7, sha256 35a5f64dec1adc110e5cd786177d2c22eca0c6c923a51b5d30f149dbf4f91ad6)
BibTeX
@misc{dce780ba7557b7,
  title = {NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models — arXiv:2610.23271},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23271},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e780ba7557b7; sha256 35a5f64dec1adc110e5cd786177d2c22eca0c6c923a51b5d30f149dbf4f91ad6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23271. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision--Language--Action (VLA) models promise generalist robotic agents, yet consolidating skills learned across heterogeneous tasks and environments remains difficult: training data is fragmented across platforms, joint multi-task training suffers from interference, and model merging tends to introduce parameter conflicts or require architectural changes. We instead advocate a paradigm in which skills are first learned independently and then consolidated post hoc. To this end, we propose NestedVLA, which replaces parameter aggregation with parameter generation: a nested hypernetwork, conditioned on the target task, synthesizes task-adaptive action-expert parameters that compose with a frozen base VLA. Task-specific compressed VLM residuals are retained separately. This formulation enables flexible task-conditioned skill reuse while mitigating interference. Across three RL benchmarks (MetaWorld, ManiSkill, CALVIN), NestedVLA outperforms the strongest model-merging baseline by 41 pp on average, matches per-task fine-tuning within 1 pp on ManiSkill, and substantially closes the gap on CALVIN, pointing toward a storage-efficient route to skill consolidation. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.23271 — 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 2026-10-19T09:17:41.711Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).