Elamur Research⌕
☰
home / authors / Ziqian Zeng

Ziqian Zeng

Ziqian Zeng has 5 papers in our library, in 2025–2026, most of them on Reasoning, Bias, fairness & safety, Language models & pretraining; often with Haoran Li, Cen Chen, Hao Peng.

5 papers in our library · 2025–2026

OpenAlex · ORCID · Wikidata · h-index 10 · 73 works · 464 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 Cited 20 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #8451

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓South China University of TechnologyGuangzhou · China2012–2026 · 69 papersEducation 2012–2016 · Bachelor, Computer Science and EngineeringEmployment since 2021 · Associated Professor, Shien Ming Wu School of Intelligent Engineeringcurrent🎓Hong Kong University of Science and TechnologyHong Kong · China2017–2022 · 11 papers
🏛️The Hong Kong University of Science and Technology School of EngineeringHong Kong · China2016–2021Education 2016–2021 · PhD, Computer Science and Engineering

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 8The field of science this work belongs to (OpenAlex fields).Computer Science · 5 worksArtificial Intelligence · 5 worksArts and Humanities · 4 worksLanguage and Linguistics · 4 worksSocial Sciences · 1 workSociology and Political Science · 1 workComputer Vision and Pattern Recognition · 1 workSoftware · 1 work

🧭 Topics 5Research subjects and languages the work is about.Language models & pretraining · 1 workBias, fairness & safety · 2 worksReasoning · 2 worksEfficient models & compression · 1 workLegal AI · 1 work

 Works by year

2020s

20262 papers20253 papers

 Papers

The most cited first (OpenAlex and our library).

  1. PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration (2025 · 13 citations)
    Cloud-hosted LLMs receive user queries that may contain sensitive details, such as diagnoses or legal facts.
  2. Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning (2025 · 7 citations)
    LLMs deployed as tool-using agents raise safety and privacy risks. Typical defenses detect sensitive patterns instead of reasoning about the situation, and they rarely reflect actual legal standards. The authors reframe safety and privacy as compliance questions grounded in Contextual Integrity (CI) theory. Under CI…
  3. MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning (2026 · 5 citations)
    Reasoning-oriented LLMs produce very long Chain-of-Thought outputs, so their KV cache consumes large amounts of GPU memory and bandwidth.
  4. SDD: Self-Degraded Defense against Malicious Fine-tuning (2025 · 4 citations)
    Open-weight LLMs that have been safety-aligned can be turned harmful again by fine-tuning them on a small amount of harmful data (malicious fine-tuning, MFT).
  5. Activation-Guided Local Editing for Jailbreaking Attacks (2026 · 1 citation)
    The paper addresses the weaknesses of current jailbreak techniques used to red-team aligned LLMs. Token-level attacks tend to yield gibberish suffixes that filters catch easily and that rarely transfer to other models. Prompt-level attacks depend on manual crafting or costly iterative search. The authors present…

All works

6 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

  1. GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetHuiping Zhuang et al.2023 · 72 citations
  2. PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and RestorationAnnual Meeting of the Association for Computational Linguistics (ACL)Ziqian Zeng, Jianwei Wang, Junyao Yang, et al.2025 · 13 citations
  3. Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement LearningConference on Empirical Methods in Natural Language Processing (EMNLP)Wenbin Hu, Haoran Li, Huihao Jing, et al.2025 · 7 citations
  4. MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Tao Zhang, Ziqian Zeng, Hao Peng, et al.2026 · 5 citations
  5. SDD: Self-Degraded Defense against Malicious Fine-tuningAnnual Meeting of the Association for Computational Linguistics (ACL)ZiXuan Chen, Weikai Lu, Xin Lin, et al.2025 · 4 citations
  6. Activation-Guided Local Editing for Jailbreaking AttacksAnnual Meeting of the Association for Computational Linguistics (ACL)Jiecong Wang, Haoran Li, Hao Peng, et al.2026 · 1 citation

 Co-authors here

12 of 15 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 20 times (of the 149,439 papers whose bibliographies we read); 6 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/ziqian-zeng/