Publications

Browse all papers, or filter by research theme. See also my Google Scholar.   † denotes equal contribution.

Preprints / Under Review
Preprint
A Sober Look at Agentic Misalignment in Automated Workflows
Wenqian Ye, et al.
Under review, 2026.
arXiv
Preprint
Demystifying and Accelerating Emergence to New Tasks in Reinforcement Learning
Wenqian Ye, et al.
Under review, 2026.
2026
KDD'26
Concept-Residual Representation Expansion for Robustness to Spurious Correlations
Eric Xie, Guangzhi Xiong, Wenqian Ye, Aidong Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026.
ECCV'26
Towards Robustness against Typographic Attack with Training-free Concept Localization
Bohan Liu, Wenqian Ye, Guangzhi Xiong, Zhenghao He, Sanchit Sinha, Aidong Zhang
European Conference on Computer Vision (ECCV), 2026.
KDD'26Oral @ NeurIPS RBFM
MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs
Wenqian Ye, Bohan Liu, Guangtao Zheng, Di Wang, Xu Cao, Yunsheng Ma, Bolin Lai, James Rehg, Aidong Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026.
arXiv Data
AAAI'26
SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias
Wenqian Ye, Di Wang, Guangtao Zheng, Bohan Liu, Aidong Zhang
AAAI Conference on Artificial Intelligence (AAAI), 2026.
arXiv
2025
NeurIPS'25
Rectifying Shortcut Behaviors in Preference-based Reward Learning
Wenqian Ye, Guangtao Zheng, Aidong Zhang
Conference on Neural Information Processing Systems (NeurIPS), 2025.
arXiv
IROS'25
On-Board Vision-Language Models (VLMs) for Personalized Motion Control of Autonomous Vehicles
Can Cui, Zichong Yang, Yupeng Zhou, Juntong Peng, Sung-Yeon Park, Cong Zhang, Yunsheng Ma, Xu Cao, Wenqian Ye, Yiheng Feng, Jitesh H. Panchal, Lingxi Li, Yaobin Chen, Ziran Wang
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025.
CIKM'25
Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be Forgotten
Wei Qian, Chenxu Zhao, Yangyi Li, Wenqian Ye, Mengdi Huai
ACM International Conference on Information and Knowledge Management (CIKM), 2025.
PDF
KDD'25🏆 Best Paper Award
Improving Group Robustness on Spurious Correlation via Evidential Alignment
Wenqian Ye, Guangtao Zheng, Aidong Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025.
Best Paper Award (1 of ~3,000 submissions).
arXiv Code
ICML'25
NeuronTune: Towards Self-Guided Spurious Bias Mitigation
Guangtao Zheng, Wenqian Ye, Aidong Zhang
International Conference on Machine Learning (ICML), 2025.
arXiv Code
IJCAI'25
ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models
Guangtao Zheng, Wenqian Ye, Aidong Zhang
International Joint Conference on Artificial Intelligence (IJCAI), 2025.
arXiv Code
COLM'25
What is the Visual Cognition Gap between Humans and Multimodal LLMs?
Xu Cao, Yifan Shen, Bolin Lai, Wenqian Ye, Yunsheng Ma, Joerg Heintz, Jintai Chen, Jianguo Cao, James M. Rehg
Conference on Language Modeling (COLM), 2025.
PDF
TMLR'25
The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning
Wenqian Ye†, Luyang Jiang†, Eric Xie†, Guangtao Zheng, Yunsheng Ma, Xu Cao, Dongliang Guo, Daiqing Qi, Zeyu He, Yijun Tian, Megan Coffee, Zhe Zeng, Sheng Li, Ting-hao (Kenneth) Huang, Ziran Wang, James M. Rehg, Henry Kautz, Aidong Zhang
Transactions on Machine Learning Research (TMLR), 2025. Shorter version at the ICML DMLR Workshop, 2024.
arXiv
WACV'25
Position: Prospective of Autonomous Driving — Multimodal LLMs, World Models, Embodied Intelligence, AI Alignment, and Mamba
Yunsheng Ma, Wenqian Ye, Can Cui, et al.
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025.
ML4H'24
Recent Advances, Applications and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at the ML4H 2024 Symposium
Amin Adibi, Xu Cao, Zongliang Ji, Jivat Neet Kaur, Winston Chen, Elizabeth Healey, Brighton Nuwagira, Wenqian Ye, et al.
Machine Learning for Health (ML4H) Symposium, Research Roundtables, 2025.
arXiv
Preprint
RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation
Zhichao Xu, Minheng Wang, Yawei Wang, Wenqian Ye, Yuntao Du, Yunpu Ma, Yijun Tian
arXiv preprint, 2025.
arXiv
2024
CVPR'24
LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs
Yunsheng Ma, Can Cui, Xu Cao, Wenqian Ye, Peiran Liu, Juanwu Lu, Amr Abdelraouf, Rohit Gupta, Kyungtae Han, Aniket Bera, James Rehg, Ziran Wang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
PDF Code
CVPR'24
MAPLM: A Real-World Large-Scale Vision-Language Dataset for Map and Traffic Scene Understanding
Xu Cao, Tong Zhou, Yunsheng Ma, Wenqian Ye, Can Cui, Kun Tang, Zhipeng Cao, Kaizhao Liang, Ziran Wang, James Rehg, Chao Zheng
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
PDF Code Data
EMNLP Findings'24
Learning Autonomous Driving Tasks via Human Feedbacks with Large Language Models
Yunsheng Ma, Xu Cao, Wenqian Ye, Can Cui, Kai Mei, Ziran Wang
Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP Findings), 2024.
PDF
ECCV'24
Benchmarking Spurious Bias in Few-Shot Image Classifiers
Guangtao Zheng, Wenqian Ye, Aidong Zhang
European Conference on Computer Vision (ECCV), 2024.
arXiv Code
KDD'24
Spuriousness-Aware Meta-Learning for Learning Robust Classifiers
Guangtao Zheng, Wenqian Ye, Aidong Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024.
arXiv Code
IJCAI'24
Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation
Guangtao Zheng, Wenqian Ye, Aidong Zhang
International Joint Conference on Artificial Intelligence (IJCAI), 2024.
arXiv Code
ML4H'24
MpoxVLM: A Vision-Language Model for Diagnosing Skin Lesions from Mpox Virus Infection
Xu Cao†, Wenqian Ye†, Kenny Moise, Megan Coffee
Machine Learning for Health Symposium (ML4H), 2024.
arXiv
ML4H'24
EHRMamba: Towards Generalizable and Scalable Foundation Models for Electronic Health Records
Adibvafa Fallahpour, Mahshid Alinoori, Wenqian Ye, Xu Cao, Arash Afkanpour, Amrit Krishnan
Machine Learning for Health Symposium (ML4H), 2024.
arXiv Code
WACVW'24
A Survey on Multimodal Large Language Models for Autonomous Driving
Can Cui†, Yunsheng Ma†, Xu Cao†, Wenqian Ye†, Yang Zhou, Kaizhao Liang, Jintai Chen, Juanwu Lu, Zichong Yang, Kuei-Da Liao, Tianren Gao, Erlong Li, Kun Tang, Zhipeng Cao, Tong Zhou, Ao Liu, Xinrui Yan, Shuqi Mei, Jianguo Cao, Ziran Wang, Chao Zheng
IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), 2024.
Preprint
Medical Video Generation for Disease Progression Simulation
Xu Cao, Kaizhao Liang, Kuei-Da Liao, Tianren Gao, Wenqian Ye, Jintai Chen, Zhiguang Ding, Jianguo Cao, James M. Rehg, Jimeng Sun
arXiv preprint, 2024.
arXiv
2023
UAI'23
Mitigating Transformer Overconfidence via Lipschitz Regularization
Wenqian Ye, Yunsheng Ma, Xu Cao, Kun Tang
Conference on Uncertainty in Artificial Intelligence (UAI), 2023.
PDF
ITSC'23
CEMFormer: Learning to Predict Driver Intentions from In-Cabin and External Cameras via Spatial-Temporal Transformers
Yunsheng Ma, Wenqian Ye, Xu Cao, Amr Abdelraouf, Kyungtae Han, Rohit Gupta, Ziran Wang
IEEE International Conference on Intelligent Transportation Systems (ITSC), 2023.
arXiv
ICASSP'23
ViTASD: Robust ViT Baselines for Autism Spectrum Disorder Facial Detection
Xu Cao†, Wenqian Ye†, Elena Sizikova, Xue Bai, Megan Coffee, Hongwu Zeng, Jianguo Cao
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023.
arXiv Code
AAAI'23 Workshop
Uncertainty Estimation in Deterministic Vision Transformer
Wenqian Ye†, Yunsheng Ma†, Xu Cao
AAAI Workshop on Uncertainty Reasoning and Quantification in Decision Making (UDM), 2023.
PDF
CoRL Workshop'23
Imagined Subgoals for Hierarchical Goal-Conditioned Policies
Xuhui Kang, Wenqian Ye, Yen-Ling Kuo
CoRL Workshop on Learning Effective Abstractions for Planning (LEAP), 2023.
OpenReview
2021
Preprint
Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models
Wenqian Ye, Fei Xu, Yaojia Huang, Cassie Huang
arXiv preprint, 2021.
arXiv
Preprints / Under Review
Preprint
A Sober Look at Agentic Misalignment in Automated Workflows
Wenqian Ye, et al.
Under review, 2026.
arXiv
Preprint
Demystifying and Accelerating Emergence to New Tasks in Reinforcement Learning
Wenqian Ye, et al.
Under review, 2026.
2026
KDD'26Oral @ NeurIPS RBFM
MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs
Wenqian Ye, Bohan Liu, Guangtao Zheng, Di Wang, Xu Cao, Yunsheng Ma, Bolin Lai, James Rehg, Aidong Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026.
arXiv Data
AAAI'26
SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias
Wenqian Ye, Di Wang, Guangtao Zheng, Bohan Liu, Aidong Zhang
AAAI Conference on Artificial Intelligence (AAAI), 2026.
arXiv
2025
NeurIPS'25
Rectifying Shortcut Behaviors in Preference-based Reward Learning
Wenqian Ye, Guangtao Zheng, Aidong Zhang
Conference on Neural Information Processing Systems (NeurIPS), 2025.
arXiv
KDD'25🏆 Best Paper Award
Improving Group Robustness on Spurious Correlation via Evidential Alignment
Wenqian Ye, Guangtao Zheng, Aidong Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025.
Best Paper Award (1 of ~3,000 submissions).
arXiv Code
ICML'25
NeuronTune: Towards Self-Guided Spurious Bias Mitigation
Guangtao Zheng, Wenqian Ye, Aidong Zhang
International Conference on Machine Learning (ICML), 2025.
arXiv Code
TMLR'25
The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning
Wenqian Ye†, Luyang Jiang†, Eric Xie†, Guangtao Zheng, Yunsheng Ma, Xu Cao, Dongliang Guo, Daiqing Qi, Zeyu He, Yijun Tian, Megan Coffee, Zhe Zeng, Sheng Li, Ting-hao (Kenneth) Huang, Ziran Wang, James M. Rehg, Henry Kautz, Aidong Zhang
Transactions on Machine Learning Research (TMLR), 2025. Shorter version at the ICML DMLR Workshop, 2024.
arXiv
2024
CVPR'24
LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs
Yunsheng Ma, Can Cui, Xu Cao, Wenqian Ye, Peiran Liu, Juanwu Lu, Amr Abdelraouf, Rohit Gupta, Kyungtae Han, Aniket Bera, James Rehg, Ziran Wang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
PDF Code
ML4H'24
MpoxVLM: A Vision-Language Model for Diagnosing Skin Lesions from Mpox Virus Infection
Xu Cao†, Wenqian Ye†, Kenny Moise, Megan Coffee
Machine Learning for Health Symposium (ML4H), 2024.
arXiv
2023
UAI'23
Mitigating Transformer Overconfidence via Lipschitz Regularization
Wenqian Ye, Yunsheng Ma, Xu Cao, Kun Tang
Conference on Uncertainty in Artificial Intelligence (UAI), 2023.
PDF
2026
KDD'26
Concept-Residual Representation Expansion for Robustness to Spurious Correlations
Eric Xie, Guangzhi Xiong, Wenqian Ye, Aidong Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026.
AAAI'26
SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias
Wenqian Ye, Di Wang, Guangtao Zheng, Bohan Liu, Aidong Zhang
AAAI Conference on Artificial Intelligence (AAAI), 2026.
arXiv
2025
KDD'25🏆 Best Paper Award
Improving Group Robustness on Spurious Correlation via Evidential Alignment
Wenqian Ye, Guangtao Zheng, Aidong Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025.
Best Paper Award (1 of ~3,000 submissions).
arXiv Code
TMLR'25
The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning
Wenqian Ye†, Luyang Jiang†, Eric Xie†, Guangtao Zheng, Yunsheng Ma, Xu Cao, Dongliang Guo, Daiqing Qi, Zeyu He, Yijun Tian, Megan Coffee, Zhe Zeng, Sheng Li, Ting-hao (Kenneth) Huang, Ziran Wang, James M. Rehg, Henry Kautz, Aidong Zhang
Transactions on Machine Learning Research (TMLR), 2025. Shorter version at the ICML DMLR Workshop, 2024.
arXiv
ICML'25
NeuronTune: Towards Self-Guided Spurious Bias Mitigation
Guangtao Zheng, Wenqian Ye, Aidong Zhang
International Conference on Machine Learning (ICML), 2025.
arXiv Code
IJCAI'25
ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models
Guangtao Zheng, Wenqian Ye, Aidong Zhang
International Joint Conference on Artificial Intelligence (IJCAI), 2025.
arXiv Code
CIKM'25
Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be Forgotten
Wei Qian, Chenxu Zhao, Yangyi Li, Wenqian Ye, Mengdi Huai
ACM International Conference on Information and Knowledge Management (CIKM), 2025.
PDF
2024
ECCV'24
Benchmarking Spurious Bias in Few-Shot Image Classifiers
Guangtao Zheng, Wenqian Ye, Aidong Zhang
European Conference on Computer Vision (ECCV), 2024.
arXiv Code
KDD'24
Spuriousness-Aware Meta-Learning for Learning Robust Classifiers
Guangtao Zheng, Wenqian Ye, Aidong Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024.
arXiv Code
IJCAI'24
Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation
Guangtao Zheng, Wenqian Ye, Aidong Zhang
International Joint Conference on Artificial Intelligence (IJCAI), 2024.
arXiv Code
2023
UAI'23
Mitigating Transformer Overconfidence via Lipschitz Regularization
Wenqian Ye, Yunsheng Ma, Xu Cao, Kun Tang
Conference on Uncertainty in Artificial Intelligence (UAI), 2023.
PDF
AAAI'23 Workshop
Uncertainty Estimation in Deterministic Vision Transformer
Wenqian Ye†, Yunsheng Ma†, Xu Cao
AAAI Workshop on Uncertainty Reasoning and Quantification in Decision Making (UDM), 2023.
PDF
Preprints / Under Review
Preprint
A Sober Look at Agentic Misalignment in Automated Workflows
Wenqian Ye, et al.
Under review, 2026.
arXiv
2026
ECCV'26
Towards Robustness against Typographic Attack with Training-free Concept Localization
Bohan Liu, Wenqian Ye, Guangzhi Xiong, Zhenghao He, Sanchit Sinha, Aidong Zhang
European Conference on Computer Vision (ECCV), 2026.
KDD'26Oral @ NeurIPS RBFM
MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs
Wenqian Ye, Bohan Liu, Guangtao Zheng, Di Wang, Xu Cao, Yunsheng Ma, Bolin Lai, James Rehg, Aidong Zhang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026.
arXiv Data
AAAI'26
SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias
Wenqian Ye, Di Wang, Guangtao Zheng, Bohan Liu, Aidong Zhang
AAAI Conference on Artificial Intelligence (AAAI), 2026.
arXiv
2025
NeurIPS'25
Rectifying Shortcut Behaviors in Preference-based Reward Learning
Wenqian Ye, Guangtao Zheng, Aidong Zhang
Conference on Neural Information Processing Systems (NeurIPS), 2025.
arXiv
Preprints / Under Review
Preprint
Demystifying and Accelerating Emergence to New Tasks in Reinforcement Learning
Wenqian Ye, et al.
Under review, 2026.
2024
ML4H'24
MpoxVLM: A Vision-Language Model for Diagnosing Skin Lesions from Mpox Virus Infection
Xu Cao†, Wenqian Ye†, Kenny Moise, Megan Coffee
Machine Learning for Health Symposium (ML4H), 2024.
arXiv
ML4H'24
EHRMamba: Towards Generalizable and Scalable Foundation Models for Electronic Health Records
Adibvafa Fallahpour, Mahshid Alinoori, Wenqian Ye, Xu Cao, Arash Afkanpour, Amrit Krishnan
Machine Learning for Health Symposium (ML4H), 2024.
arXiv Code
Preprint
Medical Video Generation for Disease Progression Simulation
Xu Cao, Kaizhao Liang, Kuei-Da Liao, Tianren Gao, Wenqian Ye, Jintai Chen, Zhiguang Ding, Jianguo Cao, James M. Rehg, Jimeng Sun
arXiv preprint, 2024.
arXiv
2023
ICASSP'23
ViTASD: Robust ViT Baselines for Autism Spectrum Disorder Facial Detection
Xu Cao†, Wenqian Ye†, Elena Sizikova, Xue Bai, Megan Coffee, Hongwu Zeng, Jianguo Cao
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023.
arXiv Code

Embodied AI & Autonomous Driving

IROS'25
On-Board Vision-Language Models (VLMs) for Personalized Motion Control of Autonomous Vehicles
Can Cui, Zichong Yang, Yupeng Zhou, Juntong Peng, Sung-Yeon Park, Cong Zhang, Yunsheng Ma, Xu Cao, Wenqian Ye, Yiheng Feng, Jitesh H. Panchal, Lingxi Li, Yaobin Chen, Ziran Wang
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025.
WACV'25
Position: Prospective of Autonomous Driving — Multimodal LLMs, World Models, Embodied Intelligence, AI Alignment, and Mamba
Yunsheng Ma, Wenqian Ye, Can Cui, et al.
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025.
CVPR'24
MAPLM: A Real-World Large-Scale Vision-Language Dataset for Map and Traffic Scene Understanding
Xu Cao, Tong Zhou, Yunsheng Ma, Wenqian Ye, Can Cui, Kun Tang, Zhipeng Cao, Kaizhao Liang, Ziran Wang, James Rehg, Chao Zheng
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
PDF Code Data
CVPR'24
LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs
Yunsheng Ma, Can Cui, Xu Cao, Wenqian Ye, Peiran Liu, Juanwu Lu, Amr Abdelraouf, Rohit Gupta, Kyungtae Han, Aniket Bera, James Rehg, Ziran Wang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
PDF Code
EMNLP Findings'24
Learning Autonomous Driving Tasks via Human Feedbacks with Large Language Models
Yunsheng Ma, Xu Cao, Wenqian Ye, Can Cui, Kai Mei, Ziran Wang
Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP Findings), 2024.
PDF
WACVW'24
A Survey on Multimodal Large Language Models for Autonomous Driving
Can Cui†, Yunsheng Ma†, Xu Cao†, Wenqian Ye†, Yang Zhou, Kaizhao Liang, Jintai Chen, Juanwu Lu, Zichong Yang, Kuei-Da Liao, Tianren Gao, Erlong Li, Kun Tang, Zhipeng Cao, Tong Zhou, Ao Liu, Xinrui Yan, Shuqi Mei, Jianguo Cao, Ziran Wang, Chao Zheng
IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), 2024.
ITSC'23
CEMFormer: Learning to Predict Driver Intentions from In-Cabin and External Cameras via Spatial-Temporal Transformers
Yunsheng Ma, Wenqian Ye, Xu Cao, Amr Abdelraouf, Kyungtae Han, Rohit Gupta, Ziran Wang
IEEE International Conference on Intelligent Transportation Systems (ITSC), 2023.
arXiv

AI for Health

COLM'25
What is the Visual Cognition Gap between Humans and Multimodal LLMs?
Xu Cao, Yifan Shen, Bolin Lai, Wenqian Ye, Yunsheng Ma, Joerg Heintz, Jintai Chen, Jianguo Cao, James M. Rehg
Conference on Language Modeling (COLM), 2025.
PDF
ML4H'24
Recent Advances, Applications and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at the ML4H 2024 Symposium
Amin Adibi, Xu Cao, Zongliang Ji, Jivat Neet Kaur, Winston Chen, Elizabeth Healey, Brighton Nuwagira, Wenqian Ye, et al.
Machine Learning for Health (ML4H) Symposium, Research Roundtables, 2025.
arXiv