ZX
Zhaohan Xi
cs.AIcs.CRcs.LGcs.CVcs.CLcs.DCcs.HCcs.NIcs.SEstat.ML
On Valency
published · living versionsW_337g285g·v1 · currentpublished
Decision Transformer with Task-Aware Representations for Offline Meta-Reinforcement Learning
with Xinbo Zhao, Yuhang Liu, Xin Zhang, Lei Le +1
1 version
Preprints & journals
30 papers in the corpus · 2020–2026Polar: LLM-Powered Synthesis of Real-World Cyber Evidence for Prioritization and Mitigation2610.07298v1 · Luoxi Tang, Yuqiao Meng, Ankita Patra et al.2026 · 0 citationsarXiv
Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory2610.07311v1 · Luoxi Tang, Yuqiao Meng, Nilesh Auradkar et al.2026 · 0 citationsarXiv
When Correct Memory Goes Wrong: Fuzzing Persistent Memory Use in LLM Agents2609.38275v1 · Yuqiao Meng, Luoxi Tang, Yingxue Zhang et al.2026 · 0 citationsarXiv
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium2605.09278v2 · Yuqiao Meng, Luoxi Tang, Sakshi Sunil Narvekar et al.2026 · 0 citationsarXiv
ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models2602.15344v1 · Mitchell Piehl, Zhaohan Xi, Zuobin Xiong et al.2026 · 0 citationsarXiv
Small Agent Group is the Future of Digital Health2602.08013v2 · Yuqiao Meng, Luoxi Tang, Dazheng Zhang et al.2026 · 0 citationsarXiv
TheraMind: a multi-LLM ensemble for accelerating drug repurposing in lung cancer via case report mining.41606131 · More, Vrushket, Lu, Lyra, Ding, Zeyu et al.2026 · 3 citationsNPJ precision oncology. 2026;10(1)
SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use2601.06366v3 · Pratyush Desai, Luoxi Tang, Yuqiao Meng et al.2026 · 0 citationsarXiv
Improving Clinical Data Accessibility Through Automated FHIR Data Transformation Tools2601.05822v2 · Adarsh Pawar, Yuqiao Meng, Luoxi Tang et al.2026 · 0 citationsarXiv
Schema-Grounded LLM Extraction for FHIR Patient Digital Twins2601.05847v2 · Rafael Brens, Yuqiao Meng, Luoxi Tang et al.2026 · 0 citationsarXiv
Smart Privacy Policy Assistant: An LLM-Powered System for Transparent and Actionable Privacy Notices2601.06357v1 · Sriharshini Kalvakuntla, Luoxi Tang, Yuqiao Meng et al.2026 · 0 citationsarXiv
Adversarial Network Imagination: Causal LLMs and Digital Twins for Proactive Telecom Mitigation2602.13203v2 · Vignesh Sriram, Yuqiao Meng, Luoxi Tang et al.2026 · 0 citationsarXiv
RiskBridge: Turning CVEs into Business-Aligned Patch Priorities2601.06201v2 · Yelena Mujibur Sheikh, Awez Akhtar Khatik, Luoxi Tang et al.2026 · 0 citationsarXiv
POLAR: Automating Cyber Threat Prioritization through LLM-Powered Assessment2510.01552v1 · Luoxi Tang, Yuqiao Meng, Ankita Patra et al.2025 · 0 citationsarXiv
All Your Knowledge Belongs to Us: Stealing Knowledge Graphs via Reasoning APIs2503.09727v1 · Zhaohan Xi2025 · 0 citationsarXiv
CyLens: Towards Reinventing Cyber Threat Intelligence in the Paradigm of Agentic Large Language Models2502.20791v2 · Xiaoqun Liu, Jiacheng Liang, Qiben Yan et al.2025 · 1 citationarXiv
Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks2410.02220v4 · Xiaoqun Liu, Jiacheng Liang, Luoxi Tang et al.2024 · 1 citationarXiv
PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning.40895426 · Zhang, Tianrong, Xi, Zhaohan, Wang, Ting et al.2025 · 1 citationProceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting. 2024;1:3212-3225
Robustifying Safety-Aligned Large Language Models through Clean Data Curation2405.19358v2 · Xiaoqun Liu, Jiacheng Liang, Muchao Ye et al.2024 · 1 citationarXiv
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks2312.09057v1 · Changjiang Li, Ren Pang, Bochuan Cao et al.2023 · 1 citationarXiv
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks2309.13256v1 · Zhaohan Xi, Tianyu Du, Changjiang Li et al.2023 · 21 citationsarXiv
On the Security Risks of Knowledge Graph Reasoning2305.02383v2 · Zhaohan Xi, Tianyu Du, Changjiang Li et al.2023 · 1 citationarXiv
Neural Architectural Backdoors2210.12179v2 · Ren Pang, Changjiang Li, Zhaohan Xi et al.2022 · 0 citationsarXiv
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning2210.07346v2 · Changjiang Li, Ren Pang, Zhaohan Xi et al.2022 · 52 citationsarXiv
Reasoning over Multi-view Knowledge Graphs2209.13702v1 · Zhaohan Xi, Ren Pang, Changjiang Li et al.2022 · 2 citationsarXiv
Seeing is Living? Rethinking the Security of Facial Liveness Verification in the Deepfake Era2202.10673v1 · Changjiang Li, Li Wang, Shouling Ji et al.2022 · 14 citationsarXiv
Towards Robust Reasoning over Knowledge Graphs2110.14693v2 · Zhaohan Xi, Ren Pang, Changjiang Li et al.2021 · 0 citationsarXiv
On the Security Risks of AutoML2110.06018v1 · Ren Pang, Zhaohan Xi, Shouling Ji et al.2021 · 5 citationsarXiv
TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors2012.09302v4 · Ren Pang, Zheng Zhang, Xiangshan Gao et al.2020 · 24 citationsarXiv
Graph Backdoor2006.11890v5 · Zhaohan Xi, Ren Pang, Shouling Ji et al.2020 · 2 citationsarXiv
Career total: 35 works. 30 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.