Split and Bridge：在采样阶段桥接预训练扩散模型的多模态生成框架
Split and Bridge: Multimodal Generation via Diffusion Bridging
做扩散模型或多模态生成的朋友可以看看这篇。它不从头联合训练，而是在采样时桥接现成的预训练模型，省掉大量训练成本，代码也开源了。想在已有模型上低成本扩展多模态能力的团队会感兴趣。
一篇来自 arXiv 的论文提出 Split and Bridge（SnB），一种自下而上的多模态生成框架。与主流自上而下方法从零联合训练共享潜变量不同，SnB 不学习统一潜空间，而是在采样时让各模态沿共享扩散轨迹走到一个分裂点，再由 bridge 模块引导分出各模态专属轨迹。这一设计让强大的预训练单模态扩散模型即插即用，无需联合训练即可复用。
在 PolyMNIST、CelebAMask-HQ 基准以及更复杂的 PIE-Bench++、ROCO 数据集上，SnB 在样本质量与多模态一致性之间取得了较好平衡。作者还展示 SnB 可自然扩展到零样本任务，包括交错式协同生成、图像编辑以及风格的耦合与解耦。代码已在 GitHub（AhmadArrabi/SnB）开源，供研究者复现与扩展。
Split and Bridge: Multimodal Generation via Diffusion Bridging
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 https://github.com/AhmadArrabi/SnB
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include 扩散模型, 多模态, diffusion, 图像生成.
Source attribution: curated from arXiv cs.LG (@Ahmad Arrabi, Xiaohan Zhang, Xingyu Li, Safwan Wshah).