ZQ

Zeyu Qin

cs.AIcs.LGcs.CLcs.CRcs.NE

On Valency

published · living versions

W_9bfw4gjt·v1 · currentpublished

Dual Exam: Controlled Evaluation of Multimodal Agents and World Models

with Zhefan Rao, Meng Chu, Xuan Zhang, Jingfan Chen +78

1 version

Preprints & journals

8 papers in the corpus · 2022–2026

AutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?2609.35025v1 · Haotian Luo, Haoyu Wang, Zeyu Qin et al.2026 · 0 citationsarXiv

Do Phone-Use Agents Respect Your Privacy?2604.00986v2 · Zhengyang Tang, Ke Ji, Xidong Wang et al.2026 · 0 citationsarXiv

Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models2506.07121v3 · Ren-Jian Wang, Ke Xue, Zeyu Qin et al.2025 · 0 citationsarXiv

Lifelong Safety Alignment for Language Models2505.20259v1 · Haoyu Wang, Zeyu Qin, Yifei Zhao et al.2025 · 0 citationsarXiv

Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense2410.09838v2 · Rui Min, Zeyu Qin, Nevin L. Zhang et al.2024 · 1 citationarXiv

Preserving Diversity in Supervised Fine-Tuning of Large Language Models2408.16673v2 · Ziniu Li, Congliang Chen, Tian Xu et al.2024 · 5 citationsarXiv

Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators2310.07289v1 · Liang Chen, Yang Deng, Yatao Bian et al.2023 · 27 citationsarXiv

Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis2210.00557v1 · Jiancong Xiao, Zeyu Qin, Yanbo Fan et al.2022 · 3 citationsarXiv

Career total: 11 works. 8 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.