Thomas Hartvigsen

Orcid: 0000-0002-5288-2792

According to our database1, Thomas Hartvigsen authored at least 89 papers between 2017 and 2025.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
Instruction-based Time Series Editing.
CoRR, August, 2025

ModelCitizens: Representing Community Voices in Online Safety.
CoRR, July, 2025

KScope: A Framework for Characterizing the Knowledge Status of Language Models.
CoRR, June, 2025

Efficient Knowledge Editing via Minimal Precomputation.
CoRR, June, 2025

Model Editing with Graph-Based External Memory.
CoRR, May, 2025

Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification.
CoRR, May, 2025

Continually Self-Improving Language Models for Bariatric Surgery Question-Answering.
CoRR, May, 2025

MedBrowseComp: Benchmarking Medical Deep Research and Computer Use.
CoRR, May, 2025

SAINT: Attention-Based Modeling of Sub-Action Dependencies in Multi-Action Policies.
CoRR, May, 2025

BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing.
CoRR, May, 2025

PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages.
CoRR, April, 2025

Inferring Event Descriptions from Time Series with Language Models.
CoRR, March, 2025

How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook.
CoRR, March, 2025

Medical Large Language Model Benchmarks Should Prioritize Construct Validity.
CoRR, March, 2025

Constrained Language Generation with Discrete Diffusion Models.
CoRR, March, 2025

Understanding the Limits of Lifelong Knowledge Editing in LLMs.
CoRR, March, 2025

Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English.
CoRR, March, 2025

Norm Growth and Stability Challenges in Localized Sequential Knowledge Editing.
CoRR, February, 2025

Sparse Autoencoder Features for Classifications and Transferability.
CoRR, February, 2025

Lifelong Sequential Knowledge Editing without Model Degradation.
CoRR, February, 2025

Learning under Temporal Label Noise.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Composable Interventions for Language Models.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Sparse MoE as a New Treatment: Addressing Forgetting, Fitting, Learning Issues in Multi-Modal Multi-Task Learning.
Proceedings of the Conference on Parsimony and Learning, 2025

Low-Bit Quantization Favors Undertrained LLMs.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Lifelong Model Editing with Graph-Based External Memory.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024
Explaining deep multi-class time series classifiers.
Knowl. Inf. Syst., June, 2024

Improving Black-box Robustness with In-Context Rewriting.
Trans. Mach. Learn. Res., 2024

Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens.
CoRR, 2024

Offline Reinforcement Learning With Combinatorial Action Spaces.
CoRR, 2024

Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing.
CoRR, 2024

Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes.
CoRR, 2024

Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation.
CoRR, 2024

SDoH-GPT: Using Large Language Models to Extract Social Determinants of Health (SDoH).
CoRR, 2024

Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding.
CoRR, 2024

PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models.
CoRR, 2024

Recent Advances, Applications, and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at ML4H 2023 Symposium.
CoRR, 2024

UniTS: Building a Unified Time Series Model.
CoRR, 2024

MATHWELL: Generating Educational Math Word Problems at Scale.
CoRR, 2024

Improving Black-box Robustness with In-Context Rewriting.
CoRR, 2024

Learning from Time Series under Temporal Label Noise.
CoRR, 2024

Are Language Models Actually Useful for Time Series Forecasting?
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

BendVLM: Test-Time Debiasing of Vision-Language Embeddings.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

UniTS: A Unified Multi-Task Time Series Model.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2024, 2024

Language Models Still Struggle to Zero-shot Reason about Time Series.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

MATHWELL: Generating Educational Math Word Problems Using Teacher Annotations.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

SkipSNN: Efficiently Classifying Spike Trains with Event-attention.
Proceedings of the IEEE International Conference on Big Data, 2024

Identifying Implicit Social Biases in Vision-Language Models.
Proceedings of the Seventh AAAI/ACM Conference on AI, Ethics, and Society (AIES-24) - Full Archival Papers, October 21-23, 2024, San Jose, California, USA, 2024

TAXI: Evaluating Categorical Knowledge Editing for Language Models.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023
Dissecting the heterogeneity of "in the wild" stress from multimodal sensor data.
npj Digit. Medicine, 2023

Machine Learning for Health symposium 2023 - Findings track.
CoRR, 2023

Continuous Time Evidential Distributions for Irregular Time Series.
CoRR, 2023

Interpretable Unified Language Checking.
CoRR, 2023

Finding Short Signals in Long Irregular Time Series with Continuous-Time Attention Policy Networks.
CoRR, 2023

Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023


Taking Off with AI: Lessons from Aviation for Healthcare.
Proceedings of the 3rd ACM Conference on Equity and Access in Algorithms, 2023

Multi-State Brain Network Discovery.
Proceedings of the IEEE International Conference on Big Data, 2023

Stabilizing Adversarial Training for Generative Networks.
Proceedings of the IEEE International Conference on Big Data, 2023

Knowledge Amalgamation for Multi-Label Classification via Label Dependency Transfer.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
Positive Unlabeled Learning with a Sequential Selection Bias.
Proceedings of the 2022 SIAM International Conference on Data Mining, 2022

TWEET-FID: An Annotated Dataset for Multiple Foodborne Illness Detection Tasks.
Proceedings of the Thirteenth Language Resources and Evaluation Conference, 2022

Class-Specific Explainability for Deep Time Series Classifiers.
Proceedings of the IEEE International Conference on Data Mining, 2022

The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations.
Proceedings of the FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21, 2022

Stop&Hop: Early Classification of Irregular Time Series.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

Robust Recurrent Classifier Chains for Multi-Label Learning with Missing Labels.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

Recovering the Propensity Score from Biased Positive Unlabeled Data.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
Recurrent Bayesian Classifier Chains for Exact Multi-Label Classification.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Energy-Efficient Models for High-Dimensional Spike Train Classification using Sparse Spiking Neural Networks.
Proceedings of the KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021

Learning Saliency Maps to Explain Deep Time Series Classifiers.
Proceedings of the CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1, 2021

Human-like Explanation for Text Classification With Limited Attention Supervision.
Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), 2021

Variational Open Set Recognition (VOSR).
Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), 2021

Semi-Supervised Knowledge Amalgamation for Sequence Classification.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Recurrent Halting Chain for Early Multi-label Classification.
Proceedings of the KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2020

Learning to Selectively Update State Neurons in Recurrent Networks.
Proceedings of the CIKM '20: The 29th ACM International Conference on Information and Knowledge Management, 2020

Clinical Performance Evaluation of a Machine Learning System for Predicting Hospital-Acquired Clostridium Difficile Infection.
Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020), 2020

Learning Similarity-Preserving Meta-Embedding for Text Mining.
Proceedings of the 2020 IEEE International Conference on Big Data (IEEE BigData 2020), 2020

Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words?
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020

2019
Adaptive-Halting Policy Network for Early Classification.
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019

Learning Temporal Relevance in Longitudinal Medical Notes.
Proceedings of the 2019 IEEE International Conference on Big Data (IEEE BigData), 2019

Patient-level Classification on Clinical Note Sequences Guided by Attributed Hierarchical Attention.
Proceedings of the 2019 IEEE International Conference on Big Data (IEEE BigData), 2019

Comparing General and Locally-Learned Word Embeddings for Clinical Text Mining.
Proceedings of the 2019 IEEE EMBS International Conference on Biomedical & Health Informatics, 2019

2018
Detecting MRSA Infections by Fusing Structured and Unstructured Electronic Health Record Data.
Proceedings of the Biomedical Engineering Systems and Technologies, 2018

Early Prediction of MRSA Infections using Electronic Health Records.
Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018), 2018

2017
CREST - Risk Prediction for Clostridium Difficile Infection Using Multimodal Data Mining.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2017


  Loading...