0

Sijia Liu

Papers
28

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
28papers

Authored papers

28

Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR

arXiv 2026

2026

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

arXiv 2025

2025

UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models

arXiv 2024

2024

SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning

arXiv 2024

2024

Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference

arXiv 2024

2024

Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning

arXiv 2024

2024

WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models

arXiv 2024

2024

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

arXiv 2024

2024

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models

arXiv 2024

2024

Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing

CVPR 2025 1

2024

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning

arXiv 2024

2024

Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency

arXiv 2024

2024

DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training

arXiv 2023

2023

AutoVP: An Automated Visual Prompting Framework and Benchmark

arXiv 2023

2023

Text-Visual Prompting for Efficient 2D Temporal Video Grounding

CVPR 2023 1

2023

Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks

arXiv 2023

2023

Can Adversarial Examples Be Parsed to Reveal Victim Model Information?

arXiv 2023

2023

From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models

arXiv 2023

2023

To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now

arXiv 2023

2023

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

arXiv 2023

2023

Model Sparsity Can Simplify Machine Unlearning

model-sparsity-can-simplify-machine

2023

Robust Mixture-of-Expert Training for Convolutional Neural Networks

ICCV 2023 1

2023

How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective

how-to-robustify-black-box-ml-models-a-zeroth

2022

Improving Bot Response Contradiction Detection via Utterance Rewriting

SIGDIAL (ACL) 2022 9

2022

Visual Prompting for Adversarial Robustness

arXiv 2022

2022

Reverse Engineering of Imperceptible Adversarial Image Perturbations

reverse-engineering-of-imperceptible

2022

Advancing Model Pruning via Bi-level Optimization

arXiv 2022

2022

DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines

arXiv 2022

2022

Affiliations

No known affiliations.

Frequent co-authors

10

from 28 papers