Medical AI
2023
[2023.03.03] Soomin Chung (presentation link) Keyword: Supervised learning, Loss
• Supervised contrastive learning. Adveances in neural information processing systems 33 (2020) (link)[2023.03.10] Junmo Kim (presentation link) Keyword: Continual Learning, Prompt-based Learning
• Learning To Prompt for Continual Learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022) (link)
[2023.03.24] Jisoo Lee (presentation link) Keyword: Diffusion model, Generative model
• Denoising Diffusion Probabilistic Model. Adveances in neural information processing systems 33 (2020) (link)
[2023.03.31] Jungyun Oh (presentation link) Keyword: Self-Supervised Learning, Anomaly Detection
• Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 13576-13586).(2022) (link)
[2023.04.07] Doyun Kwon (presentation link) Keyword: Continual learning, Training regiems
• Understanding the role of training regimes in continual learning. Advances in Neural Information Processing Systems 33 (pp. 7308-7320).(2020) (link)
[2023.05.03] Soomin Chung (presentation link) Keyword: Curriculum learning, Robust learning
• Robust curriculum learning: from clean label detection to noisy label self-correction. International Conference on Learning Representations, (2021) (link)
[2023.05.12] Junmo Kim (presentation link) Keyword: Multimodal data, Pretrained model, MIMIC-IV
• Integrated multimodal artificial intelligence framework for healthcare applications. NPJ Digital Medicine, 5, 149 (2022) (link)
[2023.05.19] Sayoon Park (presentation link) Keyword: Audio self-supervised learning, Quantization module
• wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems 33 (2020) (link)
[2023.05.26] Jisoo Lee (presentation link) Keyword: Contrastive Learning, Time-series representation learning
• TS2Vec: Towards Universal Representation of Time Series. Proceedings of the AAAI Conference on Artificial Intelligence 36, 8 (2022) (link)
[2023.06.16] Jungyun Oh (presentation link) Keyword: Multi-Time Attention Networks, Irregularly Multivariate Time-series
• Multi-time attention networks for irregularly sampled time series. arXiv preprint arXiv:2101.10318. (2021) (link)
[2023.06.23] Doyun Kwon (presentation link) Keyword: Transformer, Pre-trained Model
• A foundational vision transformer improves diagnostic performance for electrocardiograms. NPJ Digital Medicine, 6(1), 108. (2023) (link)
[2023.07.14] Soomin Chung (presentation link) Keyword : Time-series, Transformer, Representation learning
• TARNet: Task-Aware Reconstruction for Time-Series Transformer . Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, (pp. 212-220). (2022) (link)
[2023.07.21] Junmo Kim (presentation link) Keyword : Calibration
• A tutorial on calibration measurements and calibration models for clinical prediction models. Journal of the American Medical Informatics Association, 27(4) (2020) (link)
[2023.07.28] Sayoon Park (presentation link) Keyword : Audio spectrogram transformer, Self-supervised pretraining
• SSAST: Self-Supervised Audio Spectrogram Transformer. Proceedings of the AAAI Conference on Artificial Intelligence, 36, 10 (2022) (link)
[2023.08.04] Jisoo Lee (presentation link) Keyword : Tree-based models, Tabular data
• Why do tree-based models still outperform deep learning on typical tabular data? Advances in Neural Information Processing Systems, 35 (2022) (link)
[2023.08.11] Jungyun Oh (presentation link) Keyword : Semantic segmentation, Transformer
• Per-Pixel Classification is Not All You Need for Semantic Segmentation, Advances in Neural Information Processing Systems, 34 (2021) (link)
[2023.08.18] Doyun Kwon (presentation link) Keyword : Self-supervised learning, Transformer
• Masked autoencoders are scalable vision learners. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, (pp. 16000-16009) (2022) (link)
[2023.08.25] Sommin Chung (presentation link) Keyword : Longitudinal study, EHR, GAN
• Clinical-GAN : Trajectory Forecasting of Clinical Events using Transformer and Generative Adversarial Networks. Artificial Intelligence in Medicine, 138 (2023) (link)
[2023.09.01] Junmo Kim (presentation link) Keyword : Causal inference
• Toward Causal Representation Learning. Proceedings of the IEEE, 109, 5 (2021) (link)
[2023.09.07] Sayoon Park (presentation link) Keyword : Self-supervised learning
• Self-supervised learning in medicine and healthcare. Nature Biomedical Engineering, 6, 12 (2022) (link)
[2023.09.21] Jisoo Lee (presentation link) Keyword : Multimodal self-supervised learning, Transformer
• VATT : Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text. Advances in Neural Information Processing Systems, 34 (2021) (link)
[2023.10.05] Jungyun Oh (presentation link) Keyword : CNN based model refinements
• Bag of Tricks for Image Classification with Convolutional Neural Networks. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, (pp. 558-567) (2019) (link)
[2023.10.12] Doyun Kwon (presentation link) Keyword : Multi-modal, Transformer
• Multimodal Learning with Transformers: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, (2023) (link)
[2023.10.19] Sumin Chung (presentation link) Keyword : Pretraining, BERT, ECG Language Processing
• ECGBERT: Understanding Hidden Language of ECGs with Self-Supervised Representation Learning. arXiv preprint, (2023) (link)
[2023.11.2] Junmo Kim (presentation link) Keyword :
• Learning of Cluster-based Feature Importance for Electronic Health Record Time-series. International Conference on Machine Learning, PMLR, (pp. 161-179) (2022) (link)
[2023.11.9] Sayoon Park (presentation link) Keyword : Auscultation sound, Deep learning
• DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries. NPJ digital medicine, 6, 1 (2023) (link)
[2023.11.16] Jisoo Lee (presentation link) Keyword : Self-/Semi- Supervised Learning, Tabular data
• VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain. Advances in Neural Information Processing Systems, 33, (2020) (link)
[2023.11.23] Jungyun Oh (presentation link) Keyword : Time series forecasting, Isometric convolution
• MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting. International Conference on Learning Representations, (2023) (link)
[2023.12.14] Doyun Kwon (presentation link) Keyword : Self-supervised learning, Masked Time-series Modeling
• SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling. Advances in Neural Information Processing Systems, (2023) (link)
[2023.12.21] Sumin Chung (presentation link) Keyword : Domain transfer, pretraining
• One Fits All:Power General Time Series Analysis by Pretrained LM. Advances in Neural Information Processing Systems, (2023) (link)
2024
[2024.01.10] Junmo Kim (presentation link) Keyword: Digital Twin, Electronic Health Records(EHR), Pre-training
• About Digital Twin & Pretrained EHR - (1)[2024.01.10] SaYoon Park (presentation link) Keyword: EEG, Self-supervised learning, Pre-trained model
• Neuro-GPT: Developing A Foundation Model for EEG. arXiv preprint (2023) (link)[2024.01.17] Jisoo Lee (presentation link) Keyword: Multi-modal self-spervised learning, Time series
• Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series. International Conference on Machine Learning (pp. 28531-28548) (2023) (link)[2024.01.17] Jungyun Oh (presentation link) Keyword: Pruning, Depth-wise convolution
• Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization. Thirty-First International Joint Conference on Artificial Intelligence (2022) (link)[2024.01.24] Doyun Kwon (presentation link) Keyword: Transformer, Self-supervised learning, Forecasting
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformer. The Eleventh International Conference on Learning Representations (2023) (link)[2024.01.24] Soomin Chung (presentation link) Keyword: Time series, Transformer, Multi-variate
• iTransformer: Inverted Transformers Are Effective for Time Series Forecasting. The Twelfth International Conference on Learning Representations (2024) (link)[2024.01.31] Dareen Eom (presentation link) Keyword: Selective prediction, Self-evaluation, Soft prompt tuning
• Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs. Conference on Empirical Methods in Natural Language Processing (2023) (link)[2024.01.31] Chaiho Shin (presentation link) Keyword: Large corpus similarity search, In-context pre-training
• In-Context Pretraining: Language Modeling Beyond Document Boundaries. The Twelfth International Conference on Learning Representations (2024) (link)[2024.02.07] Junmo Kim (presentation link) Keyword: Digital Twin, Electronic Health Records(EHR), Pre-training
• About Digital Twin & Pretrained EHR - (2)[2024.02.07] Sayoon Park (presentation link) Keyword: Self-supervised learning, Phonocardiogram (PCG)
• On the Out-Of-Distribution Robustness of Self-Supervised Representation Learning for Phonocardiogram Signals. arXiv preprint (2023) (link)[2024.02.14] Jisoo Lee (presentation link) Keyword: Adversarial fine-tuning, Diffusion probabilistic model, Respiratory sound
• Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance. Deep Generative Models for Health Workshop NeurIPS (2023) (link)[2024.02.14] Jungyun Oh (presentation link) Keyword: Unsupervised representation learning, Temporal neighborhood
• Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding. International Conference on Learning Representations (2021) (link)[2024.02.21] Doyun Kwon (presentation link) Keyword: LLM, Multi-modal, Forecasting
• Time-LLM: Time Series Forecasting by Reprogramming Large Language Models. International Conference on Learning Representations (2024) (link)[2024.02.21] Soomin Chung (presentation link) Keyword:
• Contrastive Masked Autoencoders are Stronger Vision Learners. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023) (link)[2024.02.28] Chaiho Shin (presentation link) Keyword: Representation learning, Compositional operations in embedding space, Contrastive objective
• Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (2023) (link)[2024.02.28] Dareen Eom (presentation link) Keyword: LLM, Reasoning capability, Negative data
• Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data. Thirty-Eighth AAAI Conference on Artificial Intelligence (2024) (link)[2024.03.08] Kyuhee Lim (presentation link) Keyword: Keyword extraction, Keyword generation, Contrastive learning
• SimCKP: Simple Contrastive Learning of Keyphrase Representations. The 2023 Conference on Empirical Methods in Natural Language Processing. (2023) (link)[2024.03.15] Dongwoo Hyeon (presentation link) Keyword: Histopathology , Image retrieval, Self-supervised learning, Feature extraction
• RetCCL: Clustering-guided contrastive learning for whole-slide image retrieval. Medical Image Analysis. (2023) (link)[2024.03.15] Jisoo Lee (presentation link) Keyword: Biosignal, Cross-data Learning, Transformer
• BIOT: Biosignal Transformer for Cross-data Learning in the Wild. Advances in Neural Information Processing Systems. (2024) (link)[2024.03.22] Sayoon Park (presentation link) Keyword:
• Rethinking Pseudo Labels for Semi-supervised Object Detection. AAAI conference on artificial intelligence 36, 2 (pp. 1314-1322). (2024) (link)[2024.03.22] Junmo Kim (presentation link) Keyword:
• 논문 제출부터 게재까지의 프로세스[2024.03.29] Jungyun Oh (presentation link) Keyword: Data pruning
• Deep Learning on a Data Diet: Finding Important Examples Early in Training. Advances in Neural Information Processing Systems. (2021) (link)[2024.03.29] Doyun Kwon (presentation link) Keyword: Contrastive learning, Foundation model, Biosignals
• Large-scale Training of Foundation Models for Wearable Biosignals. International Conference on Learning Representations. (2024) (link)[2024.04.05] Soomin Chung (presentation link) Keyword: SSL, MiM, CNN
• Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling. International Conference on Learning Representations. (2023) (link)[2024.04.05] Chaiho Shin (presentation link) Keyword: LLM based dataset construction, LLM based evaluation
• Gecko: Versatile Text Embeddings Distilled from Large Language Models. arXiv preprint. (2024) (link)[2024.04.12] Dareen Eom (presentation link) Keyword: Evolutionary algorithm, Prompt engineering
• Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers. nternational Conference on Learning Representations (2024) (link)[2024.04.12] Kyuhee Lim (presentation link) Keyword: DEFT, LoRA, Active learning
• STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models. arXiv preprint. (2024) (link)[2024.05.03] Sayoon Park (presentation link) Keyword:
• Online Active Learning For Sound Event Detection. arXiv preprint. (2023) (link)[2024.05.10] Junmo Kim (presentation link) Keyword: Drug recommendation, Electronic Health Record, Graph attention network, Transformer
• REFINE: A Fine-Grained Medication Recommendation System Using Deep Learning and Personalized Drug Interaction Modeling. Advances in Neural Information Processing Systems. (2024) (link)[2024.05.10] Jisoo Lee (presentation link) Keyword: SSL, Periodic video
• CycleCL: Self-supervised Learning for Periodic Videos. IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 2861-2870). (2024) (link)[2024.05.17] Jungyun Oh (presentation link) Keyword: Continuous sampling, Interval sampling, MLP
• Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures. arXiv preprint. (2022) (link)[2024.05.17] Doyun Kwon (presentation link) Keyword: Masked modeling, Foundation model, Forecasting
• Unified Training of Universal Time Series Forecasting Transformers. arXiv preprint. (2024) (link)[2024.05.24] Soomin Chung (presentation link) Keyword: Longitudinal ECG, LMM
• Development and validation of a dynamic deep learning algorithm using electrocardiogram to predict dyskalaemias in patients with multiple visits . European Heart Journal-Digital Health, 4(1), 22-32 . (2023) (link)[2024.05.24] Chaiho Shin (presentation link) Keyword:
• Representation Deficiency in Masked Language Modeling. arXiv preprint. (2023) (link)[2024.05.31] Dareen Eom (presentation link) Keyword: Prompt Compression, Question-aware, LLM
• LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression. The 62nd Annual Meeting of the Association for Computational Linguistics and ICLR 2024 Workshop on Mathematical and Empirical Understanding of Foundation Models. (2024) (link)[2024.05.31] Kyuhee Lim (presentation link) Keyword: LLM, SQL Generation
• Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM. arXiv preprint. (2024) (link)[2024.06.07] Sayoon Park (presentation link) Keyword:
• ExBEHRT: Extended Transformer for Electronic Health Records to Predict Disease Subtypes & Progressions. International Workshop on Trustworthy Machine Learning for Healthcare. (2023) (link)[2024.06.07] Junmo Kim (presentation link) Keyword:
• Foresight—a generative pretrained transformer for modelling of patient timelines using electronic health records: a retrospective modelling study. The Lancet Digital Health, 6(4), e281-e290. (2024) (link)[2024.06.14] Jisoo Lee (presentation link) Keyword: Audio signal, Multi-instance learning (MIL) with attention mechanism, Transfer learning
• Listen2cough: Leveraging end-to-end deep learning cough detection model to enhance lung health assessment using passively sensed audio. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 5(1), 1-22. (2021) (link)[2024.06.14] Jungyun Oh (presentation link) Keyword: STAD module, MLP
• SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion. arXiv preprint. (2024) (link)