FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows

ArXi:2512.15420v2 Announce Type: replace Any-to-any generation seeks to translate between arbitrary subsets of modalities, enabling flexible cross-modal synthesis. Despite recent success, existing flow-based approaches are challenged by their inefficiency, as they require large-scale datasets often with restrictive pairing constraints, incur high computational cost from modeling joint distribution, and rely on complex multi-stage