Metraipolis › archive › dc_561e452304e5

Split and Bridge: Multimodal Generation via Diffusion Bridging — arXiv:2611.10441

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.10441
License (as archived)
CC0-1.0
Archived
2026-11-10T18:42:30.029Z
SHA-256 of the archived text
636a2f1c5a52f2149f59982b5f15a9c685f1327824626abe7720fd795c650acc
Stable URL of this page
https://metraipolis.com/documento/dc_561e452304e5

How to cite

Split and Bridge: Multimodal Generation via Diffusion Bridging — arXiv:2611.10441 — arXiv (en), https://arxiv.org/abs/2611.10441 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_561e452304e5 (Metraipolis archive dc_561e452304e5, sha256 636a2f1c5a52f2149f59982b5f15a9c685f1327824626abe7720fd795c650acc)
BibTeX
@misc{dc561e452304e5,
  title = {Split and Bridge: Multimodal Generation via Diffusion Bridging — arXiv:2611.10441},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10441},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_561e452304e5; sha256 636a2f1c5a52f2149f59982b5f15a9c685f1327824626abe7720fd795c650acc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10441. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visual data are often expressed through multiple complementary modalities (e.g., images and segmentation masks), each capturing different aspects of the same underlying structure. Most existing multimodal methods adopt a top-down paradigm, learning a shared latent variable through joint training from scratch, which limits scalability. We propose Split and Bridge (SnB), a bottom-up framework for multimodal generation that couples pretrained unimodal diffusion models at sampling time. Rather than learning a unified latent space, SnB generates coherent multimodal samples by following a shared diffusion trajectory up to a split point and then branching into modality-specific trajectories guided by a bridge module. This design enables plug-and-play reuse of powerful pretrained models without joint training, making it scalable and easily adaptable. Across standard benchmarks (PolyMNIST, CelebAMask-HQ) and more complex settings (PIE-Bench++, ROCO), SnB achieves a strong balance between sample quality and coherence. We show that SnB naturally extends to downstream zero-shot tasks such as interleaved co-generation, image editing, and style coupling/decoupling. Our results demonstrate that bottom-up generation provides a practical framework that complements existing top-down multimodal approaches. Code is available at this https URL

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); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.10441 — 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 2026-11-10T18:37:37.589Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).