Image-conditioned Video diffusion models achieve impressive visual realism but often suffer from weakened motion fidelity, e.g., reduced motion dynamics or degraded long-term temporal coherence, especially after fine-tuning. We study the problem of motion alignment in video diffusion models post-training. To address this, we introduce pixel-motion rewards based on pixel flux dynamics, capturing both instantaneous and long-term motion consistency. We further propose Smooth Hybrid Fine-tuning (SHIFT), a scalable reward-driven fine-tuning framework for video diffusion models. SHIFT fuses the normal supervised fine-tuning and advantage weighted fine-tuning into a unified framework. Benefiting from novel adversarial advantages, SHIFT improves convergence speed and mitigates reward hacking. Experiments show that our approach efficiently resolves dynamic-degree collapse in modern video diffusion models supervised fine-tuning.
@article{arxiv.2603.17426,
title = {SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning},
author = {Xi Ye and Wenjia Yang and Yangyang Xu and Xiaoyang Liu and Duo Su and Mengfei Xia and Jun Zhu},
journal= {arXiv preprint arXiv:2603.17426},
year = {2026}
}