Sijia Liu

Robust Learning from Noisily Labeled Long-Tailed Data via Fairness Regularizer AAAI 2026 BLUR: A Bi-Level Optimization Approach for LLM Unlearning EACL 2026 Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning ACL 2026 SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs? ACL 2025 Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design ICCV 2025 Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills EMNLP 2025 ID-Patch: Robust ID Association for Group Photo Personalization CVPR 2025 Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning ICML 2025 Can Adversarial Examples Be Parsed to Reveal Victim Model Information? WACV 2025 Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond ICML 2025 Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective AAAI 2025 Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models NAACL 2025 PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection CVPR 2025 When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers ICLR 2025 Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing CVPR 2025 DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training ICLR 2024 Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency ICLR 2024 LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints EMNLP 2024 SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning EMNLP 2024 CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection WACV 2024 Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios? ACL 2024 EmotionQueen: A Benchmark for Evaluating Empathy of Large Language Models ACL 2024 To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now ECCV 2024 Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning ECCV 2024 More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling NAACL 2024 Advancing the Robustness of Large Language Models through Self-Denoised Smoothing NAACL 2024 Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ICML 2024 Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference NIPS 2024 Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models NIPS 2024 WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models NIPS 2024 From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models NIPS 2024 UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models NIPS 2024 Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network NIPS 2024 What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding ICML 2024 AutoVP: An Automated Visual Prompting Framework and Benchmark ICLR 2024 SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation ICLR 2024 Towards Credible Human Evaluation of Open-Domain Dialog Systems Using Interactive Setup AAAI 2023 On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration NIPS 2023 Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning NIPS 2023 Model Sparsity Can Simplify Machine Unlearning NIPS 2023 Holistic Adversarial Robustness of Deep Learning Models AAAI 2023 AAAI New Faculty Highlights: General and Scalable Optimization for Robust AI AAAI 2023 PersLEARN: Research Training through the Lens of Perspective Cultivation ACL 2023 Text-Visual Prompting for Efficient 2D Temporal Video Grounding CVPR 2023 Understanding and Improving Visual Prompting: A Label-Mapping Perspective CVPR 2023 DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines EMNLP 2023 Robust Mixture-of-Expert Training for Convolutional Neural Networks ICCV 2023 TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization ICLR 2023 A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity ICLR 2023 What Is Missing in IRM Training and Evaluation? Challenges and Solutions ICLR 2023 Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks ICLR 2023 Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks ICML 2023 Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach ICML 2023 Adversarial Examples Can Be Effective Data Augmentation for Unsupervised Machine Learning AAAI 2022 Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations IJCAI 2022 Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach ICLR 2022 How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis ICLR 2022 Optimizer Amalgamation ICLR 2022 Reverse Engineering of Imperceptible Adversarial Image Perturbations ICLR 2022 How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective ICLR 2022 Distributed adversarial training to robustify deep neural networks at scale UAI 2022 Advancing Model Pruning via Bi-level Optimization NIPS 2022 Data-Efficient Double-Win Lottery Tickets from Robust Pre-training ICML 2022 Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free CVPR 2022 Fairness Reprogramming NIPS 2022 Proactive Image Manipulation Detection CVPR 2022 Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization ICML 2022 Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling ICML 2022 Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework ICML 2022 Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness ICML 2022 A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction NAACL 2022 Zeroth-Order Optimization for Composite Problems with Functional Constraints AAAI 2022 The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models CVPR 2021 Rate-improved inexact augmented Lagrangian method for constrained nonconvex optimization AISTATS 2021 Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot? NIPS 2021 RMSMP: A Novel Deep Neural Network Quantization Framework With Row-Wise Mixed Schemes and Multiple Precisions ICCV 2021 RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices AAAI 2021 Robust Overfitting may be mitigated by properly learned smoothening ICLR 2021 On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning ICLR 2021 Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning ICLR 2021 Generating Adversarial Computer Programs using Optimized Obfuscations ICLR 2021 Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks NIPS 2021 Self-Progressing Robust Training AAAI 2021 Fast Training of Provably Robust Neural Networks by SingleProp AAAI 2021 Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not? ICML 2021 When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning? NIPS 2021 A Compression-Compilation Framework for On-mobile Real-time BERT Applications IJCAI 2021 NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration CVPR 2021 MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge NIPS 2021 Adversarial Attack Generation Empowered by Min-Max Optimization NIPS 2021 Hidden Cost of Randomized Smoothing AISTATS 2021 Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks ICML 2020 Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case ICML 2020 Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases ECCV 2020 The Lottery Ticket Hypothesis for Pre-trained BERT Networks NIPS 2020 Sign-OPT: A Query-Efficient Hard-label Adversarial Attack ICLR 2020 Higher-Order Certification For Randomized Smoothing NIPS 2020 Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations CVPR 2020 Adversarial T-shirt! Evading Person Detectors in A Physical World ECCV 2020 Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning CVPR 2020 Training Stronger Baselines for Learning to Optimize NIPS 2020 An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices ECCV 2020 Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020 An ADMM Based Framework for AutoML Pipeline Configuration AAAI 2020 Proper Network Interpretability Helps Adversarial Robustness in Classification ICML 2020 Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing ICML 2020 Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications ICML 2019 Adversarial Robustness vs. Model Compression, or Both? ICCV 2019 Attention Neural Model for Temporal Relation Extraction NAACL 2019 On the Design of Black-Box Adversarial Examples by Leveraging Gradient-Free Optimization and Operator Splitting Method ICCV 2019 CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks AAAI 2019 Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective IJCAI 2019 signSGD via Zeroth-Order Oracle ICLR 2019 Structured Adversarial Attack: Towards General Implementation and Better Interpretability ICLR 2019 On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization ICLR 2019 ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization NIPS 2019 AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks AAAI 2019 Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization NIPS 2018 Zeroth-Order Online Alternating Direction Method of Multipliers: Convergence Analysis and Applications AISTATS 2018 MayoNLP at SemEval 2017 Task 10: Word Embedding Distance Pattern for Keyphrase Classification in Scientific Publications SEMEVAL 2017