AI RESEARCH
The Quadratic Geometry of Flow Matching: Semantic Granularity Alignment for Text-to-Image Synthesis
arXiv CS.CV
•
ArXi:2603.10785v1 Announce Type: new In this work, we analyze the optimization dynamics of generative fine-tuning. We observe that under the Flow Matching framework, the standard MSE objective can be formulated as a Quadratic Form governed by a dynamically evolving Neural Tangent Kernel (NTK). This geometric perspective reveals a latent Data Interaction Matrix, where diagonal terms represent independent sample learning and off-diagonal terms encode residual correlation between heterogeneous features. Although standard.