---
id: 20260903-T0-14
title: "I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models"
url: https://ai.daily.yangsir.net/daily/20260903-T0-14
issue_date: 2026-09-03
publish_date: 2026-09-02T04:00:00.000Z
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2609.00003
---

# I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models

arXiv:2609.00003v1 Announce Type: new Abstract: Machine unlearning studies the removal of knowledge from an AI model, making the system forget a concept it previously learned. Despite rapid progress in generative machine unlearning, the unintended degradation of semantically related concepts that sh

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2609.00003)

**详情页**：https://ai.daily.yangsir.net/daily/20260903-T0-14

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*