Does Gradient Conflict Predict the Understanding--Generation Trade-off? A Controlled Audit of Conflict-Metric Validity in Unified Multimodal Models

Title:Does Gradient Conflict Predict the Understanding--Generation Trade-off? A Controlled Audit of Conflict-Metric Validity in Unified Multimodal Models

Abstract:Unified multimodal models (UMMs) are increasingly designed around gradient conflict between understanding and generation objectives. The premise that reducing these metrics improves the downstream understanding-generation trade-off has never been tested directly. We audit it in a controlled testbed, GRIDUMM, which mirrors key structural ingredients of UMM training while making the ground-truth trade-off exactly computable. Across 63 configurations and 372 measured checkpoints, no directional conflict metric reaches an absolute Spearman correlation of 0.3 with a confidence interval excluding zero for conflict measured during training against the eventual trade-off. A dose-response intervention that monotonically suppresses conflict leaves the trade-off flat, separating correlation from causation. The norm ratio is a generation-failure detector and becomes null among configurations that master generation. Functional interference measures outperform directional conflict metrics, while training loss tracks the trade-off strongly. Our results do not show that conflict is useless; they show that its validity as a diagnostic target must be established, not assumed, and we release the audit protocol as a reusable standard.

23 pages, 10 figures, 5 tables. Code will be made publicly available upon acceptance

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)

arXiv:2609.38465 [cs.LG]

(or arXiv:2609.38465v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.38465 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.