Metraipolis › archive › dc_fc6159dc1915
Self-correction Optimization for Interleaved Multimodal Generation — arXiv:2610.10400
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10400
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:48:07.402Z
- SHA-256 of the archived text
d0e4a16578a3160c3e060c1c6631b7894f59fd2482fcf59cb0d42c153432ecf5- Stable URL of this page
https://metraipolis.com/documento/dc_fc6159dc1915
How to cite
Self-correction Optimization for Interleaved Multimodal Generation — arXiv:2610.10400 — arXiv (en), https://arxiv.org/abs/2610.10400 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc6159dc1915 (Metraipolis archive dc_fc6159dc1915, sha256 d0e4a16578a3160c3e060c1c6631b7894f59fd2482fcf59cb0d42c153432ecf5)
BibTeX
@misc{dcfc6159dc1915,
title = {Self-correction Optimization for Interleaved Multimodal Generation — arXiv:2610.10400},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10400},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc6159dc1915; sha256 d0e4a16578a3160c3e060c1c6631b7894f59fd2482fcf59cb0d42c153432ecf5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10400. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal large language models (MLLMs) have made significant progress in visual understanding and generation. However, generating interleaved image--text content remains challenging, as it requires tightly integrated multimodal understanding and generation capabilities. Although existing MLLMs provide promising solutions, most rely on additional training with augmented data, which is computationally expensive and remains limited in preserving visual subjects, temporal consistency, and physical plausibility. In this work, we propose self-correction optimization (SCO), an effective training-free method for consistent interleaved generation. SCO treats the classifier-free guidance update as a reference and performs minimal self-correction under two complementary constraints, including new-event and state-preserving constraints. Specifically, the new-event constraint promotes temporal consistency across image--text sequences, while the state-preserving constraint maintains the coherence of visual subjects throughout subsequent generation steps. Experiments on challenging interleaved multimodal generation benchmarks demonstrate significant improvements in temporal coherence and visual-subject preservation. Furthermore, SCO can be extended to video generation and improves the modeling of physically grounded processes, including robot manipulation and long-horizon handcrafting. 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/2610.10400 — 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 2026-10-08T12:18:15.493Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).