Author

Sijia Liu

h-index 5 View on Semantic Scholar

We have 1 of 7 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning

The proposed Stochastic Meta-Unlearning (SMU), a bilevel framework that uses VLM-level feedback to learn an unlearning-ready initialization, suggests that VLM-level feedback can make language-backbone unlearning more reliable and more transferable for VLMs.

Zijie Liu, Jinhao Duan, Gaowen Liu et al. · arXiv.org · 0 citations