Metraipolis › archive › dc_405f2a5021bb
Learning Manipulation-Sufficient Representations via Outcome Bottlenecks — arXiv:2609.13235
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13235
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T01:53:39.048Z
- SHA-256 of the archived text
3e08ebe3aee15d9fba776200249e96dd749cb897e2524765f0b54aa67f78792c- Stable URL of this page
https://metraipolis.com/documento/dc_405f2a5021bb
How to cite
Learning Manipulation-Sufficient Representations via Outcome Bottlenecks — arXiv:2609.13235 — arXiv (en), https://arxiv.org/abs/2609.13235 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_405f2a5021bb (Metraipolis archive dc_405f2a5021bb, sha256 3e08ebe3aee15d9fba776200249e96dd749cb897e2524765f0b54aa67f78792c)
BibTeX
@misc{dc405f2a5021bb,
title = {Learning Manipulation-Sufficient Representations via Outcome Bottlenecks — arXiv:2609.13235},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13235},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_405f2a5021bb; sha256 3e08ebe3aee15d9fba776200249e96dd749cb897e2524765f0b54aa67f78792c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13235. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Networked manipulation endpoints couple perception to actuation across compute- and bandwidth-limited links, yet commonly exchange dense geometric states optimized for fidelity rather than action outcomes. A stochastic representation is learned with a policy-free, action-conditioned outcome bottleneck: marginal outcome log-loss supplies distortion and a KL term regularizes rate. The construction is motivated by the minimal statistic that preserves the outcome distribution of every admissible action, while the implemented finite model is evaluated as a rate-regularized mixture predictor. The same encoder and outcome head support grasp selection, singleton conformal filtering, active viewpoint selection, and latent test-time adaptation. A finite-probe theorem identifies the local level-set tangent space with the null space of an outcome Jacobian. The synthetic oracle verifies this result; on scanned objects, an analytic surrogate agrees with measured simulator invariances within \(0.56^\circ\). Across 11,979 simulated grasps on 13 objects, a reconstructed-geometry wrench score attains 0.542 AUC against lift success and falls below chance on curved objects, while our representation attains 0.876. At 25\% commitment, executed-grasp success is 0.503 versus 0.984. The 512-byte interface is \(288\times\) smaller than one RGB-D frame and runs at 16\,ms per CPU decision. Independent synthetic points track the tested conformal levels; scanned-object all-pair coverage is reported as a clustered empirical diagnostic. On unseen objects, within-scene AUC falls to 0.569, and a full-feedback update raises empirical mean pairwise coverage from 0.728 to 0.883. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV). Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.13235 — 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 2026-10-16T01:25:23.713Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).