Sijia Liu
- Papers
- 28
Cite
Notes
Only stored in your browser.
Authored papers
28Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
arXiv 2026
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
arXiv 2025
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
arXiv 2024
Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
CVPR 2025 1
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
arXiv 2024
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
arXiv 2024
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
arXiv 2024
Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
arXiv 2024
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
arXiv 2024
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
arXiv 2024
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
arXiv 2024
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
arXiv 2024
Robust Mixture-of-Expert Training for Convolutional Neural Networks
ICCV 2023 1
DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training
arXiv 2023
To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now
arXiv 2023
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
arXiv 2023
Model Sparsity Can Simplify Machine Unlearning
model-sparsity-can-simplify-machine
AutoVP: An Automated Visual Prompting Framework and Benchmark
arXiv 2023
Text-Visual Prompting for Efficient 2D Temporal Video Grounding
CVPR 2023 1
Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks
arXiv 2023
Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
arXiv 2023
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
arXiv 2023
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
how-to-robustify-black-box-ml-models-a-zeroth
DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines
arXiv 2022
Advancing Model Pruning via Bi-level Optimization
arXiv 2022
Improving Bot Response Contradiction Detection via Utterance Rewriting
SIGDIAL (ACL) 2022 9
Visual Prompting for Adversarial Robustness
arXiv 2022
Reverse Engineering of Imperceptible Adversarial Image Perturbations
reverse-engineering-of-imperceptible
Affiliations
Frequent co-authors
10from 28 papers