Transition Flow Matching
This addresses a bottleneck in generative modeling for AI researchers, offering a more efficient alternative to existing flow matching methods.
The paper tackles the problem of slow generation in flow matching methods by proposing a new paradigm that directly learns the transition flow, enabling generation in a single step or at arbitrary time points. Experiments validate the effectiveness of this approach.
Mainstream flow matching methods typically focus on learning the local velocity field, which inherently requires multiple integration steps during generation. In contrast, Mean Velocity Flow models establish a relationship between the local velocity field and the global mean velocity, enabling the latter to be learned through a mathematically grounded formulation and allowing generation to be transferred to arbitrary future time points. In this work, we propose a new paradigm that directly learns the transition flow. As a global quantity, the transition flow naturally supports generation in a single step or at arbitrary time points. Furthermore, we demonstrate the connection between our approach and Mean Velocity Flow, establishing a unified theoretical perspective. Extensive experiments validate the effectiveness of our method and support our theoretical claims.