Understanding the Limits of Lifelong Knowledge Editing in LLMs
Lukas Thede, Karsten Roth, Matthias Bethge, Zeynep Akada, Tom Hartvigsen
ICML Â - International Conference on Machine Learning, 2025 [pdf]
BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing
Dongliang Guo, Mengxuan Hu, Zihan Guan, Tom Hartvigsen, Sheng Li
ICML Â - International Conference on Machine Learning, 2025 [pdf]
Medical Large Language Model Benchmarks Should Prioritize Construct Validity
Ahmed Alaa, Thomas Hartvigsen, Niloufar Golchini, Shiladitya Dutta, Frances Dean, Inioluwa Deborah Raji, Travis Zack
ICML Â - International Conference on Machine Learning, Position Paper, 2025 [pdf]
🌟 Oral Presentation 🌟
Composable Interventions for Language Models
Arinbjorn Kolbeinsson,* Kyle O'Brien,* Tianjin Huang,* Shanghua Gao, Jonathan Richard Schwarz, Shiwei Liu, Anurag Vaidya, Faisal Mahmood, Marinka Zitnik, Tianlong Chen, Tom Hartvigsen
ICLR - International Conference on Learning Representations, 2025 [pdf]
Learning from Time Series under Label Noise
Sujay Nagaraj, Walter Gerych, Sana Tonekaboni, Anna Goldenberg, Berk Ustun, Tom Hartvigsen
ICLR - International Conference on Learning Representations, 2025 [pdf]
Sparse MoE as a New Treatment: Addressing Forgetting, Fitting, Learning Issues in Multi-Modal Multi-Task Learning
Jie Peng, Kaixiong Zhou, Ruida Zhou, Thomas Hartvigsen, Yanyong Zhang, Zhangyang Wang, Tianlong Chen
CPAL - Conference on Parsimony and Learning, 2025 [pdf]
Norm Growth and Stability Challenges in Localized Sequential Knowledge Editing
Akshat Gupta, Christine Fang, Atahan Ozdemir, Michael Lu, Ahmed Alaa, Thomas Hartvigsen, Gopala Anumanchipalli
AAAI'25 Workshop on Knowledgeable Foundation Models [pdf]
🌟 Outstanding Paper Award 🌟
Evaluating and mitigating medical misinformation risk in large language models
Shan Chen, Mingye Gao, Kuleen Sasse, Thomas Hartvigsen, Brian Anthony, Lizhou Fan, Hugo Aerts, Jack Gallifant, Danielle Bitterman
AACR Special Conference in Cancer Research: Translating Targeted Therapies in Combination with Radiotherapy, 2025 [link]
PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages
Priyanshu Kumar,* Devansh Jain,* Akhila Yerukola, Liwei Jiang, Himanshu Beniwal, Thomas Hartvigsen, Maarten Sap
preprint [pdf]
Inferring Event Descriptions from Time Series with Language Models
Mingtian Tan, Mike A. Merrill, Zack Gottesman, Tim Althoff, David Evans, Tom Hartvigsen
preprint [pdf]
Disparities in LLM Reasoning Accuracy and Explanations: A Case Study
on African American English
Runtao Zhang,* Guangya Wan,* Saadia Gabriel, Sheng Li, Alex Gates, Maarten Sap, Thomas Hartvigsen
preprint [pdf]
Sparse Autoencoder Features for Classifications and Transferability
Jack Gallifant, Shan Chen, Kuleen Sasse, Hugo Aerts, Thomas Hartvigsen, Danielle S. Bitterman
preprint [pdf]
Lifelong Sequential Knowledge Editing without Model Degradation
Akshat Gupta, Phudish Prateepamornkul, Maochuan Lu, Ahmed Alaa, Thomas Hartvigsen, Gopala Anumanchipalli
preprint [pdf]
Constrained Language Generation with Discrete Diffusion Models
Michael Cardei, Jacob K Christopher, Thomas Hartvigsen, Brian R. Bartoldson, Bhavya Kailkhura, Ferdinando Fioretto
preprint [pdf]
How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook
Haoxin Liu, Harshavardhan Kamarthi, Zhiyuan Zhao, Shangqing Xu, Shiyu Wang, Qingsong Wen, Tom Hartvigsen, Fei Wang, B. Aditya Prakash
preprint [pdf]
 Are Language Models Actually Useful for Time Series Forecasting?
Mingtian Tan, Mike Merrill, Vinayak Gupta, Tim Althoff, Thomas Hartvigsen
NeurIPS (Spotlight) - Advances in Neural Information Processing Systems, 2024 [pdf]
Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks
Jack Gallifant, Shan Chen, Pedro Moreira, Nikolaj Munch, Mingye Gao, Jackson Pond, Leo Anthony Celi, Hugo Aerts, Thomas Hartvigsen, Danielle Bitterman
EMNLP - Empirical Methods for Natural Language Processing, Findings Track, Short paper, 2024 [pdf] [leaderboard]
TAXI: Evaluating Categorical Knowledge Editing for Language Models
Derek Powell, Walter Gerych, Thomas Hartvigsen
ACL - Proceedings of the Annual Meeting of the Association for Computational Linguistics, Findings track, short paper, 2024 [pdf]
Improving Black-box Robustness with In-Context Rewriting
Kyle O’Brien, Nathan Ng, Isha Puri, Jorge Mendez, Hamid Palangi, Yoon Kim, Marzyeh Ghassemi, Thomas Hartvigsen
TMLR - Transactions on Machine Learning Research, 2024 [pdf]
Demographic Bias in Misdiagnosis by Computational Pathology Models
Anurag Vaidya, Richard Chen, Drew Williamson, Andrew Song, Guillaume Jaume, Yuzhe Yang, Thomas Hartvigsen, Emma Dyer, Ming Yang Lu, Jana Lipkova, Muhammad Shaban, Tiffany Y. Chen, Faisal Mahmood
Nature Medicine, 30, pages 1174–1190 (2024) [article] [MGB News Article]
Explaining Deep Multi-Class Time Series Classifiers
Ramesh Doddaiah, Prathyush Parvatharaju, Elke Rundensteiner, Thomas Hartvigsen
KAIS - Knowledge and Information Systems, 2024 [pdf]
FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging
Kumail Alhamoud, Yasir Ghunaim, Motasem Alfarra, Thomas Hartvigsen, Philip Torr, Bernard Ghanem, Adel Bibi, Marzyeh Ghassemi
MICCAI - Medical Image Computing and Computer Assisted Intervention, 2024 [pdf]
Identifying Implicit Social Biases in Vision-Language Models
Kimia Hamidieh, Haoran Zhang, Walter Gerych, Thomas Hartvigsen and Marzyeh Ghassemi
AIES - AAAI Conference on AI, Ethics, and Society, 2024 [pdf]
SkipSNN: Efficiently Classifying Spike Trains with Event-attention
Hang Yin, Yao Su, Liping Liu, Thomas Hartvigsen, Xin Dai, and Xiangnan Kong
IEEE BigData - IEEE International Conference on Big Data, 2024 [pdf]
Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes
Bryan Christ, Zack Gottesman, Jonathan Kropko, Thomas Hartvigsen
preprint [pdf]
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing
Dongliang Guo, Mengxuan Hu, Zihan Guan, Junfeng Guo, Thomas Hartvigsen, Sheng Li
preprint [pdf]
ProCyon: A multimodal foundation model for protein phenotypes
Owen Queen, Yepeng Huang, Robert Calef, Valentina Giunchiglia, Tianlong Chen, George Dasoulas, LeAnn Tai, Yasha Ektefaie, Ayush Noori, Joseph Brown, Tom Cobley, Karin Hrovatin, Tom Hartvigsen, Fabian Theis, Bradley L. Pentelute, Vikram Khurana, Manolis Kellis, Marinka Zitnik
preprint [pdf]
Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
Xu Ouyang, Tao Ge, Thomas Hartvigsen, Zhisong Zhang, Haitao Mi, Dong Yu
preprint [pdf]
Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation
Shan Chen, Mingye Gao, Kuleen Sasse, Thomas Hartvigsen, Brian Anthony, Lizhou Fan, Hugo Aerts, Jack Gallifant, Danielle Bitterman
preprint [pdf]
Offline Reinforcement Learning with Combinatorial Action Spaces
Matthew Landers, Taylor Killian, Hugo Barnes, Thomas Hartvigsen, Afsaneh Doryab
preprint [pdf]
Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding
Shenghuan Sun, Gregory M Goldgof, Alexander Schubert, Zhiqing Sun, Thomas Hartvigsen, Atul J Butte, Ahmed Alaa
preprint [pdf]
SDoH-GPT: Using Large Language Models to Extract Social Determinants of Health
Bernardo Consoli, Xizhi Wu, Song Wang, Xinyu Zhao, Yanshan Wang, Justin Rousseau, Thomas Hartvigsen, Li Shen, Huanmei Wu, Yifan Peng, Qi Long, Tianlong Chen, Ying Ding
preprint [pdf]
Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency
Owen Queen, Thomas Hartvigsen, Teddy Koker, Huan He, Theodoros Tsiligkaridis, Marinka Zitnik
NeurIPS, 2023 (Spotlight) [pdf]
Dissecting the Heterogeneity of "In-the-Wild Stress" from Multimodal Sensor Data
Sujay Nagaraj, Sarah Goodday, Thomas Hartvigsen, Adrien Boch, Luca Foschini, Marzyeh Ghassemi, Stephen Friend, Anna Goldenberg
npj Digital Medicine, 6, Article number: 237 (2023) [pdf]
Knowledge Amalgamation for Multi-Label Classification via Label Dependency Transfer
Jidapa Thadajarassiri, Thomas Hartvigsen, Walter Gerych, Xiangnan Kong, Elke Rundensteiner
AAAI, 2023 [pdf]
Taking Off with AI: Lessons from Aviation for Healthcare
Elizabeth Bondi-Kelly, Thomas Hartvigsen, Lindsay Sanneman, Swami Sankaranarayanan, Lauren Oakden-Rayder, Leo Celi, Julie Shah, Marzyeh Ghassemi.
EAMMO, 2023 [pdf]
Multi-State Brain Network Discovery
Hang Yin, Yao Su, Xinyue Liu, Thomas Hartvigsen, Yanhua Li, and Xiangnan Kong
IEEE BigData, 2023
Stabilizing Adversarial Training for Generative Networks
Walter Gerych, Kevin Hickey, Thomas Hartvigsen, Luke Buquicchio, Abdulaziz Alajaji, Kavin Chandrasekaran, Hamid Mansoor, Emmanuel Agu, and Elke Rundensteiner
IEEE BigData, 2023
A Pipeline for Interpretable Clinical Subtyping with Deep Metric Learning
Haoran Zhang, Qixuan Jin, Thomas Hartvigsen, Miriam Udler, Marzyeh Ghassemi
ICML 2023 Workshop on Interpretable Machine Learning for Healthcare. Best Paper. [pdf]
Unraveling the Effects of Age-Based Distribution Shifts on Medical Image Classifiers
Kumail Alhamoud, Yasir Ghunaim, Motasem Alfarra, Philip Torr, Thomas Hartvigsen, Bernard Ghanema, Adel Bibi, Marzyeh Ghassemi.
MusIML Workshop at NeurIPS 2023
Identifying Implicit Social Biases in Vision-Language Models
Kimia Hamidieh, Haoran Zhang, Thomas Hartvigsen, Marzyeh Ghassemi
ICML 2023 Workshop on Data-Centric Machine Learning Research.
Finding Short Signals in Long Irregular Time Series with Continuous-Time Attention Policy Networks
Thomas Hartvigsen, Jidapa Thadajarassiri, Xiangnan Kong, Elke Rundensteiner
[preprint]
Interpretable Unified Language Checking
Tianhua Zhang, Hongyin Luo, Yung-Sung Chuang, Wei Fang, Luc Gaitskell, Thomas Hartvigsen, Xixin Wu, Danny Fox, Helen Meng, James Glass
[preprint]
Robust Recurrent Classifier Chains For Multi-Label Learning With Missing Labels
Walter Gerych, Thomas Hartvigsen, Luke Buquicchio, Emmanuel Agu, Elke Rundensteiner
CIKM, 2022. pdf
Recovering the Propensity Score from Biased Positive Unlabeled Data
Walter Gerych, Thomas Hartvigsen, Luke Buquicchio, Emmanuel Agu, Elke Rundensteiner
AAAI, 2022. Oral Spotlight. pdf
Positive Unlabeled Learning with a Sequential Selection Bias
Walter Gerych, Thomas Hartvigsen, Luke Buquicchio, Kavin Chandrasekaran, Abdulaziz Alajaji, Hamid Mansoor, Elke Rundensteiner, Emmanuel Agu
SDM, 2022. pdf
TWEET-FID: An Annotated Dataset for Multiple Foodborne Illness Detection Tasks
Ruofan Hu, Dongyu Zhang, Dandan Tao, Thomas Hartvigsen, Hao Feng, Elke Rundensteiner
LREC, 2022. pdf
On Detecting COVID-Risky Behavior from Smartphones
Thomas Hartvigsen*, Walter Gerych*, Marzyeh Ghassemi
Workshop on Epidemiology meets Data Mining and Knowledge Discovery, KDD 2022. pdf
Multimodal Checklists for Fair Clinical Decision Support
Qixuan Jin, Haoran Zhang, Thomas Hartvigsen, Marzyeh Ghassemi
Workshop on Learning from Time Series for Health, NeurIPS 2022. Oral Spotlight.
Real-world Relevance of Generative Counterfactual Explanations.
Swami Sankaranarayanan, Thomas Hartvigsen, Lauren Oakden-Rayner, Marzyeh Ghassemi, Philip Isola
Workshop on Trustworthy and Socially Responsible Machine Learning, NeurIPS 2022.
Recurrent Bayesian Classifier Chains for Exact Multi-label Classification
Walter Gerych, Thomas Hartvigsen, Luke Buquicchio, Emmanuel Agu, Elke Rundensteiner
NeurIPS, 2021. pdf
Energy-Efficient Models for High-dimensional Spike Train Classification using Sparse Spiking Neural Networks
Hang Yin, John Boaz Lee, Xiangnan Kong, Thomas Hartvigsen, Sihong Xie
KDD, 2021. pdf
Variational Open-Set Recognition
Luke Buquicchio, Walter Gerych, Kavin Chandrasekaran, Abdulaziz Alajaji, Hamid Mansoor, Thomas Hartvigsen, Emmanuel Agu, Elke Rundensteiner
IEEE BigData, 2021.
Explainable Text Classification with Partially-Labeled Human Attention
Dongyu Zhang, Cansu Sen, Jidapa Thadajarassiri, Thomas Hartvigsen, Xiangnan Kong, Elke Rundensteiner
IEEE BigData, 2021.
Recurrent Halting Chain for Early Multi-label Classification
Thomas Hartvigsen, Cansu Sen, Xiangnan Kong, Elke Rundensteiner
KDD, 2020. pdf
Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words?
Cansu Sen, Thomas Hartvigsen, Biao Yin, X. Kong, E. Rundensteiner.
ACL, 2020. pdf
Learning to Selectively Update State Neurons in Recurrent Networks
Thomas Hartvigsen, Cansu Sen, Xiangnan Kong, Elke Rundensteiner.
CIKM, 2020. pdf
Learning Similarity-Preserving Meta-Embedding for Text Mining
Jidapa Thadajarassiri, Cansu Sen, Thomas Hartvigsen, Xiangnan Kong, Elke Rundensteiner.
IEEE BigData, 2020. pdf
Clinical Performance Evaluation of a Machine Learning System for Predicting Hospital-Acquired C. Diff.
Erin Teeple, Thomas Hartvigsen, Cansu Sen, Kajal Claypool, Elke Rundensteiner.
HEALTHINF, 2020. Best poster. pdf
Adaptive-Halting Policy Network for Early Classification
Thomas Hartvigsen, Cansu Sen, Xiangnan Kong, Elke Rundensteiner.
KDD, 2019. pdf
Patient-Level Classification of Clinical Note Sequences Guided by Attributed Hierarchical Attention
Cansu Sen, Thomas Hartvigsen, Xiangnan Kong, Elke Rundensteiner.
IEEE BigData, 2019.
Learning Temporal Relevance in Longitudinal Medical Notes
Cansu Sen, Thomas Hartvigsen, Xiangnan Kong, Elke Rundensteiner.
IEEE BigData, 2019.
Comparing General and Locally-Learned Word Embeddings for Clinical Text Mining
Jidapa Thadajarassiri, Cansu Sen, Thomas Hartvigsen, Xiangnan Kong, Elke Rundensteiner.
IEEE BHI, 2019. pdf
Early Diagnosis Prediction with Recurrent Neural Networks
Daniel Johnston, Liubuo Klindziuk, Lolita Nazarov, Thomas Hartvigsen, Elke Rundensteiner.
IEEE URTC, 2019.
Detecting MRSA Infections by Fusing Structured and Unstructured Electronic Health Record Data
Thomas Hartvigsen, Cansu Sen, Elke Rundensteiner.
Communications in Computer and Information Science, Volume 2024, 2018.
Early Prediction of MRSA Infections using Electronic Health Records
Thomas Hartvigsen, Cansu Sen, Sarah Brownell, Erin Teeple, Xiangnan Kong, Elke Rundensteiner.
HEALTHINF, 2018. Best student paper runner up. pdf
Handling Missing Values in Multivariate Time Series Classification
Julia Friend, Alec Hauck, Sruthi Kurada, Cansu Sen, Thomas Hartvigsen, Elke Rundensteiner.
IEEE URTC, 2018.
CREST - Risk Prediction for Clostridium Difficile Infection Using Multimodal Data Mining
Cansu Sen, Thomas Hartvigsen, Kajal Claypool, Elke Rundensteiner.
ECML, 2017. pdf
