Researcher — paper.dinq.me

2026 顶会论文

一作ICLR 2026Poster· Social Aspects / Accountability, Transparency and Interpretability

Knowledge Externalization: Reversible Unlearning and Modular Retrieval in Multimodal Large Language Models

Jiaqi Li · Zihan You · Ruoyan Shen · Shenyu Zhang · Songlin Zhai · Yongrui Chen · Chuanyi Zhang · Jiahui Geng · Fakhri Karray · Sheng Bi · Guilin Qi

检索与知识安全可解释性OpenReview

一作ACL 2026Poster· Natural Language Processing

SGPVT : Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM Unlearning

Jiaqi Li · Zhijing Zhang · Jiahui Geng · Sheng Bi · Chuanyi Zhang · Fan Liu · Guilin Qi

摘要

Machine unlearning in multimodal large language models (MLLMs) aims to remove specific concepts while preserving overall utility. However, existing approaches focus primarily on general utility metrics, overlooking the preservation of semantically related concepts. We present the first systematic...

多模态安全可解释性OpenReview 项目页

作者位次 #2/9AAAI 2026Poster· Artificial Intelligence

Forget What Has Seen: Selective Concept Unlearning in Segmentation Foundation Models

Miaozeng Du · Jiaqi Li · Sirui Pan · Yi Zhan · Guilin Qi · Yuxin Zhang · Rihui Jin · Yinjia Shu · Qianshan Wei

安全OpenReview

Jiaqi Li

获取完整研究档案

联系方式

2026 顶会论文

Knowledge Externalization: Reversible Unlearning and Modular Retrieval in Multimodal Large Language Models

SGPVT : Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM Unlearning

Forget What Has Seen: Selective Concept Unlearning in Segmentation Foundation Models

常见合作者