Diffusion-DRF: Differentiable Reward Flow for Video Diffusion Fine-Tuning

Abstract

Direct Preference Optimization (DPO) has recently improved Text-to-Video (T2V) generation by enhancing visual fidelity and text alignment. However, current methods rely on non-differentiable preference signals from human annotations or learned reward models. This reliance makes training label-intensive, bias-prone, and easy-to-game, which often triggers reward hacking and unstable training. We propose Diffusion-DRF, a differentiable reward flow for fine-tuning video diffusion models using a frozen, off-the-shelf Vision-Language Model (VLM) as a training-free critic. Diffusion-DRF directly backpropagates VLM feedback through the diffusion denoising chain, converting logit-level responses into token-aware gradients for optimization. We propose an automated, aspect-structured prompting pipeline to obtain reliable multi-dimensional VLM feedback, while gradient checkpointing enables efficient updates through the final denoising steps. Diffusion-DRF improves video quality and semantic alignment while mitigating reward hacking and collapse -- without additional reward models or preference datasets. It is model-agnostic and readily generalizes to other diffusion-based generative tasks.