Jianzhou Wang

2026

Beyond Sample-Level Forgetting: Improving Reliability in Multimodal Unlearning

Jianzhou Wang, Yirui Wu, Lixin Yuan, WENXIAO ZHANG, Jun Liu

ICML 2026poster

Multimodal unlearning aims to eliminate specific data from pretrained multimodal models, which offers significant advantages in data privacy and model efficiency. Current methods struggle to achieve the desired properties of effectiveness, reliability and locality, due to the complex interdependency…

Cited by 0 Source ↗Scholar ↗

2025

Diffuse&Refine: Intrinsic Knowledge Generation and Aggregation for Incremental Object Detection

Jianzhou Wang, Yirui Wu, Lixin Yuan, Wenxiao Zhang, Jun Liu, Junyang Chen +2

IJCAI 2025

Incremental Object Detection(IOD) targets at progressively extending capability of object detectors to recognize new classes. However, representation confusion between old and new classes leads to catastrophic forgetting. To alleviate this problem, we propose DiffKA, with intrinsic knowledge generat

Cited by 0 Source ↗PDF ↗Scholar ↗

Beyond Sample-Level Forgetting: Improving Reliability in Multimodal Unlearning

Diffuse&amp;Refine: Intrinsic Knowledge Generation and Aggregation for Incremental Object Detection

Diffuse&Refine: Intrinsic Knowledge Generation and Aggregation for Incremental Object Detection