# Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models

arXiv: https://arxiv.org/abs/2604.16481 · HTML: https://mlsanity.com/paper/2604.16481/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 8 of its 72 references that are in the map.
- First posted on arXiv 12 Apr 2026.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 8 of 8)

- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023)
- [To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now](https://mlsanity.com/paper/2310.11868/) (2023)
- [SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models](https://mlsanity.com/paper/2503.07392/) (2025)
- [AlignGuard: Scalable Safety Alignment for Text-to-Image Generation](https://mlsanity.com/paper/2412.10493/) (2024)

## Built on by (most cited first, 1 of 1)

- [Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending](https://mlsanity.com/paper/2605.25574/) (2026)

## Abstract (arXiv)

Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable content, such as copyrighted ones. Concept erasure has emerged as a mitigation strategy, yet existing approaches struggle to balance scalability, precision, and robustness, which restricts their applicability to erasing only a few hundred concepts. To address these limitations, we present Erasing Thousands of Concepts (ETC), a scalable framework capable of erasing thousands of concepts while preserving generation quality. Our method first models low-rank concept distributions via a Student's t-distribution Mixture Model (tMM). It enables pin-point erasure of target concepts via affine optimal transport while preserving others by anchoring the boundaries of target concept distributions without pre-defined anchor concepts. We then train a Mixture-of-Experts (MoE)-based module, termed MoEraser, which removes target embeddings while preserving the anchor embeddings. By injecting noise into the text embedding projector and fine-tuning MoEraser for recovery, our framework achieves robustness to white-box attack such as module removal. Extensive experiments on over 2,000 concepts across heterogeneous domains and diffusion models demerate state-of-the-art scalability and precision in large-scale concept erasure.