cs.AINov 14, 2026

Mem2Fair: Online Fairness Control for Text-to-Video Generation via Fair Memory

Authors: Pengyu Chen, Jiaming Zhang, Xiaohua Feng, Yuyuan Li, Chaochao Chen

Organizations: Zhejiang University · Hangzhou Dianzi University

Abstract

Text-to-video (T2V) generation models can produce systematically unfair demographic outcomes when prompts leave protected attributes unspecified. For example, prompts describing nurses without specifying gender may disproportionately generate videos depicting female nurses. Mitigating unfairness in T2V generation is particularly challenging: training-based methods that modify model internals require architecture-specific access and risk disrupting temporal consistency, while sampling-based methods often incur costly pre-deployment video generation. We present the first conditional online approachability formulation of attribute-level fairness for T2V generation. Building on this formulation, we introduce Mem2Fair, a plug-and-play framework that maintains concept-conditioned Fair Memory. Using generated videos at inference time as feedback, Mem2Fair selects prompt-level attribute interventions based on the deviation from each concept's prescribed fairness target, without training or separate pre-deployment sampling. Experiments demonstrate that Mem2Fair consistently improves fairness over the unmodified generator and existing baselines across multiple demographic attributes, prompt settings, and target distributions, while maintaining comparable prompt-video alignment and video quality. We further demonstrate its effectiveness on commercial black-box T2V models.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. VARI: Robust Text-to-Video Generation via Group-Structured Intent Alignment

    Oct 13, 2026Mingxuan Zhu, Hohei Chan, Shiyuan Liu +2T2V GenerationVideo Diffusion Models

  2. HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing

    May 23, 2026Ruyi Chen, Lu Zhou, Xiaogang Xu +3T2I GenerationAlgorithmic Fairness

  3. NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation

    Aug 31, 2026Yujiang Pu, Yu KongDiffusion Model GuidanceVideo Diffusion Models