Sijia Liu
~Sijia_Liu1
30
论文总数
15.0
年均投稿
平均评分
接收情况16/30
会议分布
ICLR
18
NeurIPS
9
ICML
2
COLM
1
发表论文 (30 篇)
202514 篇
3
LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
COLM 2025Poster
4
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
ICLR 2025Oral
4
One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
NeurIPS 2025Poster
4
The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization
NeurIPS 2025Spotlight
4
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
ICML 2025Poster
4
UOE: Unlearning One Expert is Enough for Mixture-of-Experts LLMs
ICLR 2025Rejected
4
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
NeurIPS 2025Poster
5
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
ICLR 2025withdrawn
4
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
ICLR 2025Rejected
4
Visual Prompting Reimagined: The Power of Activation Prompts
ICLR 2025withdrawn
4
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
NeurIPS 2025Rejected
6
Scalable Back-Propagation-Free Training of Optical Physics-Informed Neural Networks
ICLR 2025Rejected
4
FairSkin: Fair Diffusion for Skin Disease Image Geneartion
ICLR 2025withdrawn
4
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
ICML 2025Poster
202416 篇
4
Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network
NeurIPS 2024Poster
4
AutoVP: An Automated Visual Prompting Framework and Benchmark
ICLR 2024Poster
4
What Improves the Generalization of Graph Transformer? A Theoretical Dive into Self-attention and Positional Encoding
ICLR 2024Rejected
4
Fairness Improves Learning from Noisily Labeled Long-Tailed Data
ICLR 2024Rejected
3
UGradSL: Machine Unlearning Using Gradient-based Smoothed Label
ICLR 2024Rejected
4
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
ICLR 2024Poster
4
Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective
ICLR 2024Rejected
4
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
NeurIPS 2024Poster
4
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
NeurIPS 2024Poster
4
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
ICLR 2024Spotlight
4
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
NeurIPS 2024Poster
5
Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
ICLR 2024withdrawn
4
From Trojan Horses To Castle Walls: Revealing Bilateral Backdoor Effects In Diffision Models
ICLR 2024Rejected
4
Visual Prompting Reimagined: The Power of Activation Prompts
ICLR 2024Rejected
3
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
NeurIPS 2024Poster
6
DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training
ICLR 2024Poster