PPaperPicks

Sijia Liu

Michigan State University, Department of Computer Science and Engineering, East Lansing, USA

35 papers at tracked venues · 26 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-2817-6991 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×9ICLR ×4ICML ×4ACL ×3CVPR ×3AAAI ×2ECCV ×2EMNLP ×2NAACL ×2CIKM ×1EACL ×1ICCV ×1WACV ×1

Frequent coauthors

Yihua Zhang
DBLP profile ↗ORCID search ↗
×4
Chongyu Fan
DBLP profile ↗ORCID search ↗
×4
Yimeng Zhang
DBLP profile ↗ORCID search ↗
×3
Changsheng Wang
DBLP profile ↗ORCID search ↗
×2
Hongkang Li
DBLP profile ↗ORCID search ↗
×2
Jiabao Ji
DBLP profile ↗ORCID search ↗
×2
Jinghan Jia
DBLP profile ↗ORCID search ↗
×2
Hadi Reisizadeh
DBLP profile ↗ORCID search ↗
×1
Jiaheng Wei
DBLP profile ↗ORCID search ↗
×1
Renjie Gu
DBLP profile ↗ORCID search ↗
×1
Yuguang Yao
DBLP profile ↗ORCID search ↗
×1
Hanhui Wang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. BLUR: A Bi-Level Optimization Approach for LLM Unlearning
    EACL 2026 ·
    Hadi Reisizadeh
    DBLP profile ↗ORCID search ↗
  2. ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation
    ACL 2026 ·
    Yihua Zhang
    DBLP profile ↗ORCID search ↗
  3. Robust Learning from Noisily Labeled Long-Tailed Data via Fairness Regularizer
    AAAI 2026 ·
    Jiaheng Wei
    DBLP profile ↗ORCID search ↗
  4. Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
    ACL 2026 ·
    Renjie Gu
    DBLP profile ↗ORCID search ↗
  5. Can Adversarial Examples be Parsed to Reveal Victim Model Information?
    WACV 2025 ·
    Yuguang Yao
    DBLP profile ↗ORCID search ↗
  6. Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
    CVPR 2025 ·
    Hanhui Wang
    DBLP profile ↗ORCID search ↗
  7. FROG: Fair Removal on Graph
    CIKM 2025 ·
    Ziheng Chen
    DBLP profile ↗ORCID search ↗
  8. ID-Patch: Robust ID Association for Group Photo Personalization
    CVPR 2025 ·
    Yimeng Zhang
    DBLP profile ↗ORCID search ↗
  9. Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
    ICML 2025 ·
    Changsheng Wang
    DBLP profile ↗ORCID search ↗
  10. Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design
    ICCV 2025 ·
    Yuhao Sun
    DBLP profile ↗ORCID search ↗
  11. One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
    NeurIPS 2025 ·
    Mohan Zhang
    DBLP profile ↗ORCID search ↗
  12. PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
    CVPR 2025 ·
    Wei Li
    DBLP profile ↗ORCID search ↗
  13. Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
    EMNLP 2025 ·
    Changsheng Wang
    DBLP profile ↗ORCID search ↗
  14. SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?
    ACL 2025 ·
    Haomin Zhuang
    DBLP profile ↗ORCID search ↗
  15. Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
    NeurIPS 2025 ·
    Chongyu Fan
    DBLP profile ↗ORCID search ↗
  16. The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization
    NeurIPS 2025 ·
    Yihua Zhang
    DBLP profile ↗ORCID search ↗
  17. Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
    ICML 2025 ·
    Chongyu Fan
    DBLP profile ↗ORCID search ↗
  18. Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective
    AAAI 2025 ·
    Can Jin
    DBLP profile ↗ORCID search ↗
  19. When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
    ICLR 2025 ·
    Hongkang Li
    DBLP profile ↗ORCID search ↗
  20. Advancing the Robustness of Large Language Models through Self-Denoised Smoothing
    NAACL 2024 ·
    Jiabao Ji
    DBLP profile ↗ORCID search ↗
  21. Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
    ICLR 2024 ·
    Soumyadeep Pal
    DBLP profile ↗ORCID search ↗
  22. Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
    ECCV 2024 ·
    Chongyu Fan
    DBLP profile ↗ORCID search ↗
  23. DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training
    ICLR 2024 ·
    Aochuan Chen
    DBLP profile ↗ORCID search ↗
  24. Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
    NeurIPS 2024 ·
    Yimeng Zhang
    DBLP profile ↗ORCID search ↗
  25. From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
    NeurIPS 2024 ·
    Zhuoshi Pan
    DBLP profile ↗ORCID search ↗
  26. More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling
    NAACL 2024 ·
    Bingsheng Yao
    DBLP profile ↗ORCID search ↗
  27. Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
    NeurIPS 2024 ·
    Jiabao Ji
    DBLP profile ↗ORCID search ↗
  28. Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
    ICML 2024 ·
    Yihua Zhang
    DBLP profile ↗ORCID search ↗
  29. SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
    EMNLP 2024 ·
    Jinghan Jia
    DBLP profile ↗ORCID search ↗
  30. SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
    ICLR 2024 ·
    Chongyu Fan
    DBLP profile ↗ORCID search ↗
  31. To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy to Generate Unsafe Images ... For Now
    ECCV 2024 ·
    Yimeng Zhang
    DBLP profile ↗ORCID search ↗
  32. Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network
    NeurIPS 2024 ·
    Xiao Guo
    DBLP profile ↗ORCID search ↗
  33. UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
    NeurIPS 2024 ·
    Yihua Zhang
    DBLP profile ↗ORCID search ↗
  34. WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
    NeurIPS 2024 ·
    Jinghan Jia
    DBLP profile ↗ORCID search ↗
  35. What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
    ICML 2024 ·
    Hongkang Li
    DBLP profile ↗ORCID search ↗