Fine-tuning pre-trained diffusion and flow models to optimize downstream utilities is central to real-world deployment. Existing entropy-regularized methods primarily maximize expected reward, providing no mechanism to shape tail behavior. However, tail control is often essential: the lower tail determines reliability by limiting low-reward failures, while the upper tail enables discovery by prioritizing rare, high-reward outcomes. In this work, we present Tail-aware Flow Fine-Tuning (TFFT), a principled and efficient distributional fine-tuning algorithm based on the Conditional Value-at-Risk (CVaR). We address two distinct tail-shaping goals: right-CVaR for seeking novel samples in the high-reward tail and left-CVaR for controlling worst-case samples in the low-reward tail. Unlike prior approaches that rely on non-linear optimization, we leverage the variational dual formulation of CVaR to decompose it into a decoupled two-stage procedure: a lightweight one-dimensional threshold optimization step, and a single entropy-regularized fine-tuning process via a specific pseudo-reward. This decomposition achieves CVaR fine-tuning efficiently with computational cost comparable to standard expected fine-tuning methods. We demonstrate the effectiveness of TFFT across illustrative experiments, high-dimensional text-to-image generation, and molecular design.

@inproceedings{wang2026efficient,
	title={Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning},
	author={Wang, Zifan and De Santi, Riccardo and Mo, Xiaoyu and Zavlanos, Michael M and Krause, Andreas and Johansson, Karl H},
	booktitle={International Conference on Machine Learning (ICML)},
	year={2026},
	month={July},
	pdf={https://arxiv.org/abs/2602.16796},
}