Metraipolis › archive › dc_6e54caaa6495
Prism: Bidirectional Self-Teaching for Unified Multimodal Models — arXiv:2611.06343
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06343
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:17:54.503Z
- SHA-256 of the archived text
58d711b5c4e633f4bf97df8f6b34e6915aaf6369bcc63db8c2378968a5a9c4da- Stable URL of this page
https://metraipolis.com/documento/dc_6e54caaa6495
How to cite
Prism: Bidirectional Self-Teaching for Unified Multimodal Models — arXiv:2611.06343 — arXiv (en), https://arxiv.org/abs/2611.06343 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6e54caaa6495 (Metraipolis archive dc_6e54caaa6495, sha256 58d711b5c4e633f4bf97df8f6b34e6915aaf6369bcc63db8c2378968a5a9c4da)
BibTeX
@misc{dc6e54caaa6495,
title = {Prism: Bidirectional Self-Teaching for Unified Multimodal Models — arXiv:2611.06343},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06343},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6e54caaa6495; sha256 58d711b5c4e633f4bf97df8f6b34e6915aaf6369bcc63db8c2378968a5a9c4da},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06343. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Unified Multimodal Models (UMMs) aim to support visual understanding and generation within a single model. Existing post-training methods either use understanding as a fixed teacher to improve generation, or rely on ground-truth trajectories to supervise both understanding and generation. Prism instead derives bidirectional supervision from self-generated interleaved rollouts, constructing training targets according to the reliability of their text and image chains. We propose Prism, a bidirectional self-teaching post-training method for UMMs. Like a prism decomposing mixed light, Prism decouples a coupled interleaved trajectory into a text chain and an image chain, assesses the reliability of each chain, and constructs a corresponding training target from their reliability states. Experiments on both SenseNova-U1 and BAGEL show that Prism improves both understanding and generation. On the generation side, GenEval improves from 85.8 to 89.2 (+3.4), and DPG improves from 86.1 to 87.3 (+1.2) on SenseNova-U1. On the understanding side, the total MME score improves from 2282.6 to 2311.6, and MMVP improves from 58.0 to 62.0. Consistent improvements are observed on BAGEL. These results highlight that Prism enables coordinated improvements in generation and understanding by constructing reliability-guided self-training targets from self-generated trajectories, without relying on an external verifier or externally annotated corrected trajectories during target construction. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.06343 — 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 2026-11-05T18:12:49.055Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).