Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal Models

Excerpt

arXiv:2609.38485v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) train image understanding and autoregressive image generation on shared parameters, and the two objectives are known to interfere. Existing diagnoses and remedies operate at the resolution of layers or experts, measuring conflict per layer and resolving it by separating parameters. We argue that this resolution hides an orthogonal axis. Generation in a UMM is next-token prediction over a raster sequence of visual