PPaperPicks

Shiqing Ma

University of Massachusetts Amherst, Manning College of Information & Computer Sciences, Amherst, MA, USA

19 papers at tracked venues · 15 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-1551-8948 ↗Google Scholar ↗Homepage ↗

Venues

CVPR ×5ACL ×4AAAI ×2ICLR ×2NAACL ×2CIKM ×1ECCV ×1ICML ×1NeurIPS ×1

Frequent coauthors

Zhenting Wang
DBLP profile ↗ORCID search ↗
×4
Weipeng Jiang
DBLP profile ↗ORCID search ↗
×3
Yuan Xiao
DBLP profile ↗ORCID search ↗
×3
Tingxu Han
DBLP profile ↗ORCID search ↗
×2
Xiaoyu Zhang
DBLP profile ↗ORCID search ↗
×2
Siyuan Cheng
DBLP profile ↗ORCID search ↗
×2
Hanrong Zhang
DBLP profile ↗ORCID search ↗
×1
Qingcheng Zeng
DBLP profile ↗ORCID search ↗
×1
Shengwei An
DBLP profile ↗ORCID search ↗
×1

Papers

  1. False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models
    ACL 2026 ·
    Weipeng Jiang
    DBLP profile ↗ORCID search ↗
  2. From Chaos to Clarity: A Knowledge Graph-Driven Audit Dataset Generation Framework for LLM Unlearning
    AAAI 2026 ·
    Weipeng Jiang
    DBLP profile ↗ORCID search ↗
  3. Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets
    ACL 2026 ·
    Yuan Xiao
    DBLP profile ↗ORCID search ↗
  4. An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer
    NAACL 2025 ·
    Weipeng Jiang
    DBLP profile ↗ORCID search ↗
  5. Continuous Concepts Removal in Text-to-image Diffusion Models
    NeurIPS 2025 ·
    Tingxu Han
    DBLP profile ↗ORCID search ↗
  6. Data-centric NLP Backdoor Defense from the Lens of Memorization
    NAACL 2025 ·
    Zhenting Wang
    DBLP profile ↗ORCID search ↗
  7. Invisible Backdoor Attack against Self-supervised Learning
    CVPR 2025 ·
    Hanrong Zhang
    DBLP profile ↗ORCID search ↗
  8. MLLM-as-a-Judge for Image Safety without Human Labeling
    CVPR 2025 ·
    Zhenting Wang
    DBLP profile ↗ORCID search ↗
  9. STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning
    ICLR 2025 ·
    Xiaoyu Zhang
    DBLP profile ↗ORCID search ↗
  10. The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation
    ACL 2025 ·
    Xiaoyu Zhang
    DBLP profile ↗ORCID search ↗
  11. Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone
    CVPR 2025 ·
    Yuan Xiao
    DBLP profile ↗ORCID search ↗
  12. Token-Budget-Aware LLM Reasoning
    ACL 2025 ·
    Tingxu Han
    DBLP profile ↗ORCID search ↗
  13. Uncertainty Quantification for Multiple-Choice Questions is Just One-Token Deep
    CIKM 2025 ·
    Qingcheng Zeng
    DBLP profile ↗ORCID search ↗
  14. DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models
    ICLR 2024 ·
    Zhenting Wang
    DBLP profile ↗ORCID search ↗
  15. Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
    AAAI 2024 ·
    Shengwei An
    DBLP profile ↗ORCID search ↗
  16. How to Trace Latent Generative Model Generated Images without Artificial Watermark?
    ICML 2024 ·
    Zhenting Wang
    DBLP profile ↗ORCID search ↗
  17. Lotus: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
    CVPR 2024 ·
    Siyuan Cheng
    DBLP profile ↗ORCID search ↗
  18. Towards General Robustness Verification of MaxPool-Based Convolutional Neural Networks via Tightening Linear Approximation
    CVPR 2024 ·
    Yuan Xiao
    DBLP profile ↗ORCID search ↗
  19. UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
    ECCV 2024 ·
    Siyuan Cheng
    DBLP profile ↗ORCID search ↗