Yujun Zhou

21 papers A* 5B 1Journal 13Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
Capability-Oriented Training Induced Alignment Risk.
CoRR
Yujun Zhou, Yue Huang, Han Bao, Kehan Guo, Zhenwen Liang, Pin-Yu Chen, Tian Gao, Werner Geyer, Nuno Moniz, Nitesh V. Chawla, Xiangliang Zhang
2026 J jnl
Position: General Alignment Has Hit a Ceiling; Edge Alignment Must Be Taken Seriously.
CoRR
Han Bao, Yue Huang, Xiaoda Wang, Zheyuan Zhang, Yujun Zhou, Carl Yang, Xiangliang Zhang, Yanfang Ye
2025 J jnl
Artificial Intelligence in Spectroscopy: Advancing Chemistry from Prediction to Generation and Beyond.
CoRR
Kehan Guo, Yili Shen, Gisela Abigail Gonzalez-Montiel, Yue Huang, Yujun Zhou, Mihir Surve, Zhichun Guo, Payel Das, Nitesh V. Chawla, Olaf Wiest, Xiangliang Zhang
2025 J jnl
Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosis.
CoRR
Yicheng Lang, Kehan Guo, Yue Huang, Yujun Zhou, Haomin Zhuang, Tianyu Yang, Yao Su, Xiangliang Zhang
2025 — conf
Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study.
EMNLP (Findings)
Yujun Zhou, Jiayi Ye, Zipeng Ling, Yufei Han, Yue Huang, Haomin Zhuang, Zhenwen Liang, Kehan Guo, Taicheng Guo, Xiangqi Wang, Xiangliang Zhang
2025 J jnl
Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study.
CoRR
Yujun Zhou, Jiayi Ye, Zipeng Ling, Yufei Han, Yue Huang, Haomin Zhuang, Zhenwen Liang, Kehan Guo, Taicheng Guo, Xiangqi Wang, Xiangliang Zhang
2025 J jnl
Exploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVR.
CoRR
Haomin Zhuang, Yujun Zhou, Taicheng Guo, Yue Huang, Fangxu Liu, Kai Song, Xiangliang Zhang
2025 J jnl
Position: We Need An Adaptive Interpretation of Helpful, Honest, and Harmless Principles.
CoRR
Yue Huang, Chujie Gao, Yujun Zhou, Kehan Guo, Xiangqi Wang, Or Cohen-Sasson, Max Lamparth, Xiangliang Zhang
2024 A* conf
Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data.
ICML
Yujun Zhou, Yufei Han, Haomin Zhuang, Hongyan Bao, Xiangliang Zhang
2024 A* conf
Can LLMs Solve Molecule Puzzles? A Multimodal Benchmark for Molecular Structure Elucidation.
NeurIPS
Kehan Guo, Bozhao Nan, Yujun Zhou, Taicheng Guo, Zhichun Guo, Mihir Surve, Zhenwen Liang, Nitesh V. Chawla, Olaf Wiest, Xiangliang Zhang
2024 A* conf
Defending Jailbreak Prompts via In-Context Adversarial Game.
EMNLP
Yujun Zhou, Yufei Han, Haomin Zhuang, Kehan Guo, Zhenwen Liang, Hongyan Bao, Xiangliang Zhang
2024 J jnl
Defending Jailbreak Prompts via In-Context Adversarial Game.
CoRR
Yujun Zhou, Yufei Han, Haomin Zhuang, Taicheng Guo, Kehan Guo, Zhenwen Liang, Hongyan Bao, Xiangliang Zhang
2024 J jnl
LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs.
CoRR
Yujun Zhou, Jingdong Yang, Kehan Guo, Pin-Yu Chen, Tian Gao, Werner Geyer, Nuno Moniz, Nitesh V. Chawla, Xiangliang Zhang
2024 — conf
SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark.
ACL (Short Papers)
Zhenwen Liang, Kehan Guo, Gang Liu, Taicheng Guo, Yujun Zhou, Tianyu Yang, Jiajun Jiao, Renjie Pi, Jipeng Zhang, Xiangliang Zhang
2024 J jnl
SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark.
CoRR
Zhenwen Liang, Kehan Guo, Gang Liu, Taicheng Guo, Yujun Zhou, Tianyu Yang, Jiajun Jiao, Renjie Pi, Jipeng Zhang, Xiangliang Zhang
2024 J jnl
Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?
CoRR
Yue Huang, Zhengqing Yuan, Yujun Zhou, Kehan Guo, Xiangqi Wang, Haomin Zhuang, Weixiang Sun, Lichao Sun, Jindong Wang, Yanfang Ye, Xiangliang Zhang
2023 A* conf
Towards Efficient and Domain-Agnostic Evasion Attack with High-Dimensional Categorical Inputs.
AAAI
Hongyan Bao, Yufei Han, Yujun Zhou, Xin Gao, Xiangliang Zhang
2022 B conf
AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical Applications with Categorical Inputs.
IEEE Big Data
Helene Orsini, Hongyan Bao, Yujun Zhou, Xiangrui Xu, Yufei Han, Longyang Yi, Wei Wang, Xin Gao, Xiangliang Zhang
2022 J jnl
AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical Applications with Categorical Inputs.
CoRR
Helene Orsini, Hongyan Bao, Yujun Zhou, Xiangrui Xu, Yufei Han, Longyang Yi, Wei Wang, Xin Gao, Xiangliang Zhang
2022 J jnl
Towards Efficient and Domain-Agnostic Evasion Attack with High-dimensional Categorical Inputs.
CoRR
Hongyan Bao, Yufei Han, Yujun Zhou, Xin Gao, Xiangliang Zhang
2022 A* conf
Towards Understanding the Robustness Against Evasion Attack on Categorical Data.
ICLR
Hongyan Bao, Yufei Han, Yujun Zhou, Yun Shen, Xiangliang Zhang