SOURCE-LINKED INTELLIGENCE

There and Back Again: Bidirectional Diffusion Bridges for Multimodality Translation

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Multimodality translation (e.g., text-to-image) is a core generative AI task. However, existing approaches (1) follow generative paths that do not directly represent the source modality, limiting the flexibility of some sampling algorithms; and (2) are unidirectional, preventing inversion (e.g., image-to-text). We propose BIT: Bidirectional Image-Text Diffusion Bridges. In contrast to previous approaches, BIT starts directly from text and interpolates into images, providing (1) a source-aware generative path that enables diverse and flexible sampling algorithms; and (2) an endpoint-conditioned

Read original source ↗ Open in workspace

recordType

paper

region

Global