Metraipolis › archive › dc_c09d1ed5e8a3

Learning to Group and Order: Cross-Instance Self-Supervised RL for Vision-Centric MLLMs — arXiv:2611.00892

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00892
License (as archived)
CC0-1.0
Archived
2026-11-03T11:40:49.535Z
SHA-256 of the archived text
c233513f5662b0dd5ec40e435199fce3342f31a71d58271ef862d7d1540116c7
Stable URL of this page
https://metraipolis.com/documento/dc_c09d1ed5e8a3

How to cite

Learning to Group and Order: Cross-Instance Self-Supervised RL for Vision-Centric MLLMs — arXiv:2611.00892 — arXiv (en), https://arxiv.org/abs/2611.00892 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c09d1ed5e8a3 (Metraipolis archive dc_c09d1ed5e8a3, sha256 c233513f5662b0dd5ec40e435199fce3342f31a71d58271ef862d7d1540116c7)
BibTeX
@misc{dcc09d1ed5e8a3,
  title = {Learning to Group and Order: Cross-Instance Self-Supervised RL for Vision-Centric MLLMs — arXiv:2611.00892},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00892},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c09d1ed5e8a3; sha256 c233513f5662b0dd5ec40e435199fce3342f31a71d58271ef862d7d1540116c7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00892. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reinforcement learning (RL) post-training has become an important paradigm for improving multimodal large language models (MLLMs), especially with automatically verifiable rewards. Self-supervised visual pretext tasks provide such rewards without human annotations. However, existing methods mainly exploit within-instance structure, offering limited supervision for cross-instance discrimination and fine-grained comparison. We introduce Group-and-Order Self-Supervised Reinforcement Learning (GO-SSL), a cross-instance jigsaw framework for vision-centric MLLM post-training. Given two visual instances, GO-SSL mixes their local elements and trains the model to group them by instance of origin while recovering the order within each group, coupling instance-level comparison with spatial, temporal, or geometric structure recovery. This paired formulation turns the same unlabeled data into richer verifiable supervision through diverse pairings, shuffles, and a random-to-hard curriculum. We instantiate GO-SSL mainly on cross-image jigsaw tasks and further extend it to 3D depth and video temporal ordering. Across diverse benchmarks, GO-SSL consistently improves over the base MLLM and prior self-supervised post-training baselines, with clear gains in fine-grained perception and spatial understanding. Further evaluations across model scales and families support its generality. These results suggest that cross-instance comparison provides a useful self-supervised RL signal for improving transferable visual understanding in MLLMs. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.00892 — 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 2026-11-03T11:06:37.456Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).