Multi-objective alignment for text-to-image generation is commonly implemented via static linear scalarization, but fixed weights often fail under heterogeneous rewards, leading to optimization imbalance where models overfit high-variance, high-responsiveness objectives (e.g., OCR) while under-optimizing perceptual goals. We identify two mechanistic causes: variance hijacking, where reward dispersion induces implicit reweighting that dominates the normalized training signal, and gradient conflicts, where competing objectives produce opposing update directions and trigger seesaw-like oscillations. We propose APEX (Adaptive Priority-based Efficient X-objective Alignment), which stabilizes heterogeneous rewards with Dual-Stage Adaptive Normalization and dynamically schedules objectives via P^3 Adaptive Priorities that combine learning potential, conflict penalty, and progress need. On Stable Diffusion 3.5, APEX achieves improved Pareto trade-offs across four heterogeneous objectives, with balanced gains of +1.31 PickScore, +0.35 DeQA, and +0.53 Aesthetics while maintaining competitive OCR accuracy, mitigating the instability of multi-objective alignment.
@article{arxiv.2601.06574,
title = {APEX: Learning Adaptive Priorities for Multi-Objective Alignment in Vision-Language Generation},
author = {Dongliang Chen and Xinlin Zhuang and Junjie Xu and Luojian Xie and Zehui Wang and Jiaxi Zhuang and Haolin Yang and Liang Dou and Xiao He and Xingjiao Wu and Ying Qian},
journal= {arXiv preprint arXiv:2601.06574},
year = {2026}
}