Conference/Journal Papers [google scholar]

(* indicates equal contributions)

Preprint

• MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent MemoryMinghao Guo, Qingyue Jiao, Zeru Shi, Yihao Quan, Boxuan Zhang, Danrui Li, Liwei Che, Wujiang Xu, Shilong Liu, Zirui Liu, Mubbasir Kapadia, Vladimir Pavlovic, Jiang Liu, Mengdi Wang, Yiyu Shi, Dimitris N. Metaxas, and Ruixiang TangArxiv Preprint
• AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent SystemsBoxuan Zhang, Jianing Zhu, Zeru Shi, Dongfang Liu, Ruixiang TangArxiv Preprint
• Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional ShiftsBoxuan Zhang, Jianing Zhu, Jiang Liu, Zhangyang Wang, Ruixiang TangArxiv Preprint
• Enhancing Multi-modal Reasoning via Self-Revisiting Image EvidenceZeru Shi, Kai Mei, Yihao Quan, Dimitris N. Metaxas, Ruixiang TangArxiv Preprint
• Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM ReasoningZeru Shi, Yingjia Wan, Zhenting Wang, Qifan Wang, Fan Yang, Elisa Kreiss, Ruixiang TangArxiv Preprint
• Where Fake Citations Are Made: Tracing Field-Level Hallucination to Specific Neurons in LLMsYuefei Chen, Yihao Quan, Ruixiang TangArxiv Preprint
• Q-Bridge: Code Translation for Quantum Machine Learning via LLMsRunjia Zeng, Priyabrata Senapati, Ruixiang Tang, Dongfang Liu, Qiang GuanArxiv Preprint
• Sweeping Promptable Spoofs under the DirtyRAG: A Practical, Query-Blind RAG Attack Done RightShaochen Zhong, Jiamu Zhang, Hoang Anh Duy Le, Wenya Xie, Yifan Lu, Xintong Sun, Mohsen Hariri, Hongyi Liu, Guanchu Wang, Zhaozhuo Xu, Zirui Liu, Shuai Xu, Ning Xie, Li Li, Rui Chen, Ruixiang Tang, Xia Hu, Vipin ChaudharyArxiv Preprint
• Data Augmentation for High-Fidelity Generation of CAR-T Immunological Synapse ImagesXiang Zhang, Boxuan Zhang, Alireza Naghizadeh, Mohab Mohamed, Ruixiang Tang, Dimitris Metaxas, Dongfang LiuResearchgate Preprint
• What Shapes a Creative Machine Mind? Comprehensively Benchmarking Creativity in Foundation ModelsZicong He, Boxuan Zhang, Weihao Liu, Ruixiang Tang, Lu ChengArxiv Preprint

Publications

2026

• TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State ModelingJiaqian Li, Yanshu Li, Boxuan Zhang, Ruixiang Tang, Kuan-Hao HuangEmpirical Methods in Natural Language Processing, EMNLP Main, 2025
• Reinforcing Consistency in Video MLLMs with Structured RewardsYihao Quan, Zeru Shi, Jinman Zhao, Ruixiang TangConference on Language Modeling, COLM, 2026
• From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation EngineeringRui Wu, Ruixiang TangConference on Language Modeling, COLM, 2026
• Personalize Your Large Vision-language Models With In-context Prompt TuningYanshu Li, Jiaqian Li, Kuai Yu, Xi Xiao, Dongfang Liu, Tianyang Wang, Ruixiang TangThe European Conference on Computer Vision, ECCV, 2026
• HIVE: Understanding Post Hallucination Reasoning in Vision Language ModelsFeng He, Zhenting Wang, Qifan Wang, Qiang Guan, Dongfang Liu, Ruixiang Tang, Qiankun LiThe European Conference on Computer Vision, ECCV, 2026
• Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language ModelsLiwei Che*, Zhiyu Xue*, Yihao Quan*, Benlin Liu, Zeru Shi, Ruixiang Tang, Ranjay Krishna, Vladimir PavlovicThe European Conference on Computer Vision, ECCV, 2026
• A Single Layer to Explain Them All: Understanding Massive Activations in Large Language ModelsZeru Shi, Zhenting Wang, Fan Yang, Qifan Wang, Ruixiang TangThe International Conference on Machine Learning, ICML, 2026
• Towards Generalizable Implicit In-Context Learning with Attention RoutingJiaqian Li*, Yanshu Li*, Ligong Han, Ruixiang Tang, Wenya WangThe International Conference on Machine Learning, ICML, 2026
• Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM SafetyCan Jin*, Rui Wu*, Tong Che*, Qixin Zhang, Hongwu Peng, Jiahui Zhao, Zhenting Wang, Wenqi Wei, Ligong Han, Zhao Zhang, Yuan Cao, Ruixiang Tang, Dimitris N MetaxasAssociation for Computational Linguistics, ACL Main, 2026
• Read the Scene, Not the Script: Outcome-Aware Safety for LLMsRui Wu, Yihao Quan, Zeru Shi, Zhenting Wang, Yanshu Li, Ruixiang TangInternational Conference on Learning Representations, ICLR AIWILD Workshop, (Spotlight)
• Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA ModelYanchuan Tang*, Taowen Wang*, Yuefei Chen, Boxuan Zhang, Qiang Guan, Ruixiang TangIEEE International Conference on Multimedia and Expo, ICME, 2026 (Best Paper Candidate)
• CounterVQA: Evaluating and Improving Counterfactual Reasoning in Vision-Language Models for Video UnderstandingYuefei Chen, Jiang Liu, Xiaodong Lin, Ruixiang TangConference on Computer Vision and Pattern Recognition, CVPR Findings, 2026
• CAMA: Enhancing Multimodal In-Context Learning with Context-Aware Modulated AttentionYanshu Li, Jianjiang Yang, Ziteng Yang, Bozheng Li, Hongyang He, Zhengtao Yao, Ligong Han, Yingjie Victor Chen, Songlin Fei, Dongfang Liu, Ruixiang TangAnnual AAAI Conference on Artificial Intelligence, AAAI, 2026 (Oral)
• CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language ModelsYuefei Chen, Jing Ma, Vivek Singh, Ruixiang TangAnnual AAAI Conference on Artificial Intelligence, AAAI, 2026
• CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In‐Context LearningYanshu Li, Jianjiang Yang, Zhennan Shen, Ligong Han, Haoyan Xu, Ruixiang TangAnnual AAAI Conference on Artificial Intelligence, AAAI, 2026 (Oral)
• TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token DitchingRunjia Zeng, Qifan Wang, Qiang Guan, Ruixiang Tang, Lifu Huang, Zhenting Wang, Xueling Zhang, Cheng Han, Dongfang LiuInternational Conference on Learning Representations, ICLR, 2026
• FaithLM: Towards Faithful Explanations for Large Language ModelsYu-Neng Chuang*, Guanchu Wang*, Chia-Yuan Chang, Ruixiang Tang, Shaochen Zhong, Fan Yang, Andrew Wen, Mengnan Du, Xuanting Cai, Vladimir Braverman, Xia HuEuropean Chapter of the Association for Computational Linguistics, EACL, 2026

2025

• TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence ConfigurationYanshu Li, Tian Yun, Jianjiang Yang, Pinyuan Feng, Jinfa Huang, Ruixiang TangEmpirical Methods in Natural Language Processing, EMNLP Main, 2025
• LoRA-as-an-Attack! Piercing LLM Safety Under The Share-and-Play ScenarioHongyi Liu, Zirui Liu, Ruixiang Tang, Jiayi Yuan, Shaochen Zhong, Yu-Neng Chuang, Li Li, Rui Chen, Xia HuEmpirical Methods in Natural Language Processing, EMNLP Findings, 2025
• A Decoupled Multi-Agent Framework for Complex Text Style TransferLingxi Zhang, Yu-Neng Chuang, Guanchu Wang, Ruixiang Tang, Xuanting Cai, Rajesh Shenoy, Xia HuEmpirical Methods in Natural Language Processing, EMNLP Findings, 2025
• Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in RoboticsTaowen Wang, Dongfang Liu, James Chenhao Liang, Wenhao Yang, Qifan Wang, Cheng Han, Jiebo Luo, Ruixiang TangInternational Conference on Computer Vision, ICCV, 2025
• EAZY: Eliminating Hallucinations in LVLMs by Zeroing out Hallucinatory Image TokensLiwei Che, Tony Qingze Liu, Jing Jia, Weiyi Qin, Ruixiang Tang, Vladimir PavlovicInternational Conference on Computer Vision, ICCV, 2025
• When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated ExplanationsHuaizhi Ge, Yiming Li, Qifan Wang, Yongfeng Zhang, Ruixiang TangAssociation for Computational Linguistics, ACL Main, 2025
• Disentangling Memory and Reasoning Ability in Large Language ModelsMingyu Jin, Weidi Luo, Sitao Cheng, Xinyi Wang, Wenyue Hua, Ruixiang Tang, William Yang Wang, Yongfeng ZhangAssociation for Computational Linguistics, ACL Main, 2025
• SafePersuasion: A Dataset, Taxonomy, and Baselines for Analysis of Rational Persuasion and ManipulationHaein Kong, A M Muntasir Rahman, Ruixiang Tang, Vivek SinghAsia-Pacific Chapter of the Association for Computational Linguistics, AACL Findings, 2025
• Survey and Improvement Strategies for Gene Prioritization with Large Language ModelsMatthew Neeley*, Guantong Qi*, Guanchu Wang*, Ruixiang Tang, Dongxue Mao, Chaozhong Liu, Sasidhar Pasupuleti, Bo Yuan, Fan Xia, Pengfei Liu, Zhandong Liu, Xia HuBioinformatics Advances
• Uncertainty Quantification for Multiple-Choice Questions is Just One-Token DeepQingcheng Zeng, Mingyu Jin, Qinkai Yu, Zhenting Wang, Wenyue Hua, Zihao Zhou, Guangyan Sun, Yanda Meng, Shiqing Ma, Qifan Wang, Felix Juefei-Xu, Kaize Ding, Fan Yang, Ruixiang Tang, Yongfeng ZhangConference on Information and Knowledge Management, CIKM, 2025
• M2IV: Towards Efficient and Fine-grained Multimodal InContext Learning in Large Vision-Language ModelsYanshu Li, Hongyang He, Yi Cao, Qisen Cheng, Xiang Fu, Ruixiang TangConference on Language Modeling, COLM, 2025
• Massive Values in Self-Attention Modules are the Key to Contextual Knowledge UnderstandingMingyu Jin, Kai Mei, Wujiang Xu, Mingjie Sun, Ruixiang Tang, Mengnan Du, Zirui Liu, and Yongfeng Zhang.International Conference on Machine Learning, ICML 2025
• Re-Imagining Multimodal Instruction Tuning: A Representation ViewYiyang Liu, James Chenhao Liang, Ruixiang Tang, Yugyung Lee, Majid Rabbani, Sohail Dianat, Raghuveer Rao, Lifu Huang, Dongfang Liu, Qifan Wang, Cheng HanInternational Conference on Learning Representations, ICLR 2025
• DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding ModelsZihao Li, Ruixiang Tang, Lu Cheng, Shuaiqiang Wang, Dawei Yin, Mengnan DuSIGKDD Explorations, 20252024SPeC: A Soft Prompt-Based Calibration on Mitigating Performance Variability in Clinical Notes Summarization

2024

• SPeC: A Soft Prompt-Based Calibration on Mitigating Performance Variability in Clinical Notes SummarizationYu-Neng Chuang, Ruixiang Tang, Xiaoqian Jiang, Xia HuJournal of Biomedical Informatics, JBI 2024
• Taylor Unswift: Secured Weight Release for Large Language Models via Taylor ExpansionGuanchu Wang*, Yu-Neng Chuang*, Ruixiang Tang, Shaochen Zhong, Jiayi Yuan, Hongye Jin, Zirui Liu, Vipin Chaudhary, Shuai Xu, James Caverlee, Xia HuProceedings of Empirical Methods in Natural Language Processing, EMNLP 2024
• Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language ModelsYuqing Zhou, Ruixiang Tang, Ziyu Yao, Ziwei ZhuFindings of Empirical Methods in Natural Language Processing, EMNLP 2024
• TrustAgent: Towards Safe and Trustworthy LLM-based Agents through Agent ConstitutionWenyue Hua, Xianjun Yang, Mingyu Jin, Wei Cheng, Ruixiang Tang, Yongfeng ZhangFindings of Empirical Methods in Natural Language Processing, EMNLP 2024
• Fair-RGNN: Mitigating Relational Bias on Knowledge GraphsYu-Neng Chuang, Kwei-Herng Lai, Ruixiang Tang, Mengnan Du, Chia-Yuan Chang, Na Zou, Xia HuTransactions on Knowledge Discovery from Data, TKDD 2024
• Secure Your Model: An Effective Key Prompt Protection Mechanism for Large Language ModelsRuixiang Tang*, Yu-Neng Chuang*, Xuanting Cai, Mengnan Du, Xia HuFindings of Annual Conference of the North American Chapter of the ACL, NAACL 2024
• Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and BeyondJinfeng Yang*, Hongye Jin*, Ruixiang Tang*, Xiaotian Han*, Qizhang Feng*, Haoming Jiang, Xia Hu.Transactions on Knowledge Discovery from Data, TKDD 2024

2023

• Assessing Privacy Risks in Language Models: A Case Study on Summarization TasksRuixiang Tang, Gord Lueck, Rodolfo Quispe, Huseyin A Inan, Janardhan Kulkarni, Xia HuFindings of Empirical Methods in Natural Language Processing, EMNLP 2023
• Setting the Trap: Capturing and Defeating Backdoor Threats in Pretrained Language Models through HoneypotsRuixiang Tang*, Jiayi Yuan*, Yiming Li, Zirui Liu, Rui Chen, Xia HuConference on Neural Information Processing Systems, NeurIPS 2023
• Does Synthetic Data of LLMs Help Clinical Text Mining?Ruixiang Tang*, Xiaotian Han*, Xiaoqian Jiang, Xia HuAMIA 2023 Annual Symposium
• LLM for Healthcare Data Augmentation: An Example on Patient-Trial MatchingJiayi Yuan, Ruixiang Tang, Xiaoqian Jiang, Xia HuAMIA 2023 Annual Symposium (Best Student Paper )
• Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
• The Science of Detecting LLM-Generated TextRuixiang Tang, Yu-Neng Chuang, Xia HuCommunications of the ACM, 2023
• Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context LearningRuixiang Tang, Dehan Kong, Longtao Huang, Hui XueFindings of Annual Meeting of the Association for Computational Linguistics, ACL 2023
• Exposing Model Theft: A Robust and Transferable Watermark for Thwarting Model Extraction AttacksRuixiang Tang*, Hongye Jin*, Curtis Wigington, Mengnan Du, Rajiv Jain, Xia HuConference on Information and Knowledge Management, short paper, CIKM 2023
• DiscoverPath: A Knowledge Refinement and Retrieval System for Interdisciplinarity on Biomedical ResearchYu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Kwei-Herng Lai, Ruixiang Tang, Fan Yang, Alfredo Costilla Reyes, Kaixiong Zhou, Xiaoqian Jiang, Xia Hu.Conference on Information and Knowledge Management, demo paper, CIKM 2023 (Best Demo Paper Honorable Mention)
• PheME: A Deep Ensemble Framework for Improving Phenotype Prediction from Multi-modal DataShenghan Zhang*, Haoxuan Li*, Ruixiang Tang*, Sirui Ding*, Laila Rasmy, Degui Zhi, Na Zou, Xia Hu.IEEE International Conference on Healthcare Informatics, ICHI, 2023
• Deep Serial Number: Computational Watermark for DNN Intellectual Property ProtectionRuixiang Tang, Mengnan Du, Xia Hu.European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2023
• Local Contrastive Learning for Medical Image RecognitionSyed A. Rizvi, Ruixiang Tang, Xiaoqian Jiang, Xiaotian Ma, Xia HuAMIA 2023 Annual Symposium
• Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor WatermarkingRuixiang Tang, Qizhang Feng, Ninghao Liu, Fan Yang, Xia HuSIGKDD Exploration Letter, 2023

2022

• Fairly Predicting Graft Failure in Liver Transplant for Organ AssigningSirui Ding, Ruixiang Tang, Daochen Zha, Na Zou, Kai Zhang, Xiaoqian Jiang, Xia HuAMIA 2022 Annual Symposium (Best Student Paper Finalists )
• Towards Debiasing DNN Models From Spurious Feature InfluenceMengnan Du, Ruixiang Tang, Weijie Fu, Xia HuAAAI, 2022

2021

• Defense Against Explanation ManipulationRuixiang Tang*, Ninghao Liu*, Fan Yang, Na Zou, Xia HuFrontiers in Big Data, 2021
• Mitigating Gender Bias in Captioning SystemsRuixiang Tang, Mengnan Du, Yuening Li, Zirui Liu, Na Zou, Xia HuThe Web Conference, WWW 2021
• Fairness via Representation NeutralizationMengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Awadallah, Xia HuConference on Neural Information Processing Systems, NeurIPS 2021
• DEGREE: Decomposition Based Explanation for Graph Neural NetworksQizhang Feng, Ninghao Liu, Fan Yang, Ruixiang Tang, Mengnan Du, Xia HuInternational Conference on Learning Representations, ICLR 2021
• Understanding Social Biases Behind Location Names in Contextual Word Embedding ModelsFangsheng Wu, Mengnan Du, Chao Fan, Ruixiang Tang, Yang Yang, Ali Mostafavi, Xia HuIEEE Transactions on Computational Social Systems, 2021

2020 and before

• An Embarrassingly Simple Approach for Trojan Attack in Deep Neural NetworksRuixiang Tang, Mengnan Du, Ninghao Liu, Fan Yang, Xia HuACM International Conference on Knowledge Discovery & Data Mining, KDD 2020
• Breast Mass Detection in Mammograms via Blending Adversarial LearningChunze Lin, Ruixiang Tang, Darryl D Lin, Langechuan Liu, Jiwen Lu, Yunqiang Chen, Dashan Gao, Jie ZhouInternational Workshop on Simulation and Synthesis in Medical Imaging, 2020
• Deep Feature Disentanglement Learning for Bone Suppression in Chest RadiographsChunze Lin, Ruixiang Tang, Darryl D Lin, Langechuan Liu, Jiwen Lu, Yunqiang Chen, Dashan Gao, Jie ZhouIEEE International Symposium on Biomedical Imaging, ISBI 2020
• Classification of Chest CT Using Case-level Weak SupervisionRuixiang Tang, FI Tushar, S Han, R Hou, GD Rubin, JY LoSPIE Medical Imaging: Computer-Aided Diagnosis, 2019
• Multi-organ Segmentation for Patient-specific Image Quality and Dose MetrologyWanyi Fu, Shobhit Sharma, Taylor Smith, Rui Hou, Ehsan Abadi, Vignesh Selvakumaran, Ruixiang Tang, Joseph Y Lo, W Paul Segars, Anuj J Kapadia, Justin B Solomon, Geoffrey D Rubin, Ehsan SameiSPIE Medical Imaging: Physics of Medical Imaging, 2019