Author

Tianqing Zhu

h-index 19 View on Semantic Scholar

We have 3 of 138 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning May 2024

Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning

A concept-guided poisoning unlearning framework that explicitly identifies the concepts that contribute most strongly to the target class or knowledge and uses them to guide the model update, achieving effective unlearning across different tasks while largely preserving retained model utility.

Wenhan Chang, Tian-Qing Zhu, Heng Xu et al. · arXiv.org · 10 citations

2026

Parameter-Efficient Retriever-Reader for Trustworthy Table-Text Question Answering Toward Agentic Edge Intelligence

Resource-constrained edge intelligence increasingly requires lightweight and trustworthy access to heterogeneous knowledge, where decisions often involve reasoning over structured tables and associated text. In this paper, trustworthiness is operationalized as robustness under weak supervision, imperfect evidence selec...

Jian Lyu, Jingfeng Xue, Thar Baker et al. · IEEE Transactions on Network... · 0 citations

Preprint Aug 2026

BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes

Experiments show that BASIS maintains near-perfect injection detection while substantially reducing over-refusal on safe attack samples, especially under robust instruction templates.

Lai-Qiao Qin, Tianqing Zhu, Longxiang Gao et al. · 1 citation · ⚡1