Publications

31 results for Sijia Liu

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
- - Changsheng Wang
  - Yihua Zhang
  - et al.
- 2025
- ICML 2025
Rethinking Unlearning for Large Reasoning Models Download PDF
- - Changsheng Wang
  - Chongyu Fan
  - et al.
- 2025
- ICML 2025
Noisy But Forgotten: LLM Unlearning are Robust against Perturbed Data in the Wild
- - Changsheng Wang
  - Yihua Zhang
  - et al.
- 2025
- ICML 2025
PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
- - Wei Li
  - Pin-Yu Chen
  - et al.
- 2025
- CVPR 2025
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
- - Hongkang Li
  - Yihua Zhang
  - et al.
- 2025
- ICLR 2025
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
- - Jinghan Jia
  - Jiancheng Liu
  - et al.
- 2024
- NeurIPS 2024
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
- - Jiabao Ji
  - Yujian Liu
  - et al.
- 2024
- NeurIPS 2024
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
- - Yihua Zhang
  - Pingzhi Li
  - et al.
- 2024
- ICML 2024
What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
- - Hongkang Li
  - Meng Wang
  - et al.
- 2024
- ICML 2024
Machine Unlearning in Computer Vision: Foundations and Applications
- - Sijia Liu
  - Yang Liu
  - et al.
- 2024
- CVPR 2024