paper-with-me

홈 › Papers

MoESD: Mixture of Experts Stable Diffusion to Mitigate Gender Bias

2024-06-25 · Guorun Wang, Lucia Specia

Text-to-image models are known to propagate social biases. For example, when prompted to generate images of people in certain professions, these models tend to systematically generate specific genders or ethnicities. In this paper, we show that this bias is already present in the text encoder of the model and introduce a Mixture-of-Experts approach by identifying text-encoded bias in the latent space and then creating a Bias-Identification Gate mechanism. More specifically, we propose MoESD (Mixture of Experts Stable Diffusion) with BiAs (Bias Adapters) to mitigate gender bias in text-to-image models. We also demonstrate that introducing an arbitrary special token to the prompt is essential during the mitigation process. With experiments focusing on gender bias, we show that our approach successfully mitigates gender bias while maintaining image quality.

📄 PDF Abstract BibTeX arXiv:2407.11002

Code (0)

등록된 구현이 없습니다.

Tasks

Mixture-of-Experts

Similar Papers 제목 키워드 기반

Tempo as the Stable Cue: Hierarchical Mixture of Tempo and Beat Experts for Music to 3D Dance Generation

2025-12-21 · Guangtao Lyu, Chenghao Xu, Qi Liu, Jiexi Yan 외 arxiv

Music to 3D dance generation aims to synthesize realistic and rhythmically synchronized human dance from music. While existing methods often rely on additional genre labels to further improve dance generation, such label…

Abstracting Robot Manipulation Skills via Mixture-of-Experts Diffusion Policies

2026-01-29 · Ce Hao, Xuanran Zhai, Yaohua Liu, Harold Soh arxiv

Diffusion-based policies have recently shown strong results in robot manipulation, but their extension to multi-task scenarios is hindered by the high cost of scaling model size and demonstrations. We introduce Skill Mix…

Multi-Task LearningRobot ManipulationTransfer Learning

Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection

2024-09-23 · Alireza Ganjdanesh, Yan Kang, Yuchen Liu, Richard Zhang 외

Diffusion probabilistic models can generate high-quality samples. Yet, their sampling process requires numerous denoising steps, making it slow and computationally intensive. We propose to reduce the sampling cost by pru…

Denoising

Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts

2025-10-27 · Di Zhang, Xun Wu, Shaohan Huang, Lingjie Jiang 외 arxiv

Recent advances in reinforcement learning (RL) have substantially improved the training of large-scale language models, leading to significant gains in generation quality and reasoning ability. However, most existing res…

Reinforcement Learning

Language-Conditioned Representations and Mixture-of-Experts Policy for Robust Multi-Task Robotic Manipulation

2025-10-28 · Xiucheng Zhang, Yang Jiang, Hongwei Qing, Jiashuo Bai arxiv

Perceptual ambiguity and task conflict limit multitask robotic manipulation via imitation learning. We propose a framework combining a Language-Conditioned Visual Representation (LCVR) module and a Language-conditioned M…