Publications


Journal Papers

  • D. Mulders, B. Seymour, A. Mouraux, F.Mancini
    Confidence of probabilistic predictions modulates the cortical response to pain.,
    PNAS (2023)
  • F. Mancini, S. Zhang, B. Seymour
    Computational and neural mechanisms of statistical pain learning.,
    Nature Communications (2022)
  • A. Yaman, N. Bredeche, O. Çaylak, J. Z. Leibo, S. W. Lee
    Meta-control of social learning strategies.,
    PLoS Computational Biology (2022)
  • J. G. Choy, G. Cha, S. Oh
    Unsupervised 3D Link Segmentation of Articulated Objects with a Mixture of Coherent Point Drift.,
    IEEE Robotics and Automation Letters (2022)
  • Y. J. Rah, J. Kim, S. A. Lee
    Effects of spatial boundaries on episodic memory development.,
    Child Development (2022)
  • T. Kang, et al.
    Team Tidyboy at the WRS 2020: a modular software framework for home service robots.,
    Advanced Robotics (2022)
  • M. Lee, S. -W. Lee
    Quantifying arousal and awareness in altered states of consciousness using interpretable deep learning,
    Nature Communications (2021)
  • D. J. Kim, J. S. Jeong, S. W. Lee
    Prefrontal solution to the bias-variance tradeoff during reinforcement learning
    Cell Reports (2021)
  • P. Bertens, S. -W. Lee
    Network of evolvable neural units can learn synaptic learning rules and spiking dynamics,
    Nature Machine Intelligence (2020) (Cover Paper)
  • D. J. Kim, G. Y. Park, John P. O., S. W. Lee
    Task complexity interacts with state-space uncertainty in the arbitration between model-based and model-free learning,
    Nature Communications (Dec 2019)
  • H-G Jung., S. -W. Lee.
    Few-Shot Learning with Geometric Constraints,
    IEEE Transactions on Neural Networks and Learning Systems (2020)
  • S. Heo., Y. Sung., S. W. Lee.
    Effects of subclinical depression on prefrontal-striatal model-based and model-free learning,
    PLOS Computational Biology (2021)
  • G. Kim., H-G Jung., S. -W. Lee.
    Spatial reasoning for few-shot object detection,
    Pattern Recognition (2021)
  • J-W Seo., H-G Jung., S. -W. Lee.
    Self-Augmentation: Generalizing Deep Networks to Unseen Classes for Few-Shot Learning,
    Neural Networks (2021)
  • K. W. Park., J. W. Ha., J. H. Lee., S. Kwon., K. M. Kim, B.-T. Zhang.
    M2FN: Multi-step modality fusion for advertisement image assessment,
    Applied Soft Computing Journal (2021)
  • J. W. Seo., S. W. Lee.,
    Neural network-based intuitive physics for non-inertial reference frames
    IEEE Access, vol. 9, pp. 114246-114254 (2021).
  • Zhang, S., Yoshida, W., Mano, H., Yanagisawa, T., Mancini, F., Shibata, K., et al.
    Pain control by co-adaptive learning in a brain-machine interface,
    Current Biology, 1–18.(2020)
  • Yanagisawa, T., Fukuma, R., Seymour, B., Tanaka, M., Hosomi, K., Yamashita, O., et al.
    BCI training to move a virtual hand reduces phantom limb pain,
    Neurology, 95(4), e417–e426.(2020)
  • Seymour, B., Mancini, F.
    Hierarchical models of pain: Inference, information-seeking, and adaptive control.,
     NeuroImage, 222, 117212.(2020)
  • Becker, S., Löffler, M., Seymour, B.
    Reward enhances pain discrimination in humans.
    Psychological Science, 31(9), 1191–1199. (2020)
  • E. W. Kim., M. S. Lee., S. H. Oh.,
    Nonconvex Sparse Representation with Slowly Vanishing Gradient Regularizers
    IEEE Access, vol. 8, pp. 132489-132501 (2020).
  • F. Ke., S. Choi., Y. H. Kang., K. A. Cheon., S. W. Lee
    Exploring the Structural and Strategic Bases of Autism Spectrum Disorders with Deep Learning,
    IEEE Access, vol. 8, pp. 153341-153352 (2020).
  • M. R. Song., S. W. Lee.,
    Dynamic resource allocation during reinforcement learning accounts for ramping and phasic dopamine activity,
    Neural Networks, vol. 126, pp. 95-107 (2020).
  • Marilina Mastrogiuseppe, Natasha Bertelsen, Maria Francesca Bedeschi, S. A. Lee.
    The spatiotemporal organization of episodic memory and its disruption in a neurodevelopmental disorder,
    Scientific Reports 9.1 (2019): 1-12. (Dec 2019)
  • E. W. Kim., M. S. Lee., S. H. Oh.,
    A Scalable Framework for Data-Driven Subspace Representation and Clustering,
    Pattern Recognition Letters, vol. 125, pp. 742-749, (Jul. 2019).
  • ์ •์ฑ„์œค, ํ™์œ ์ •, ๊ณต์„ฑํ˜„, ์ตœ์œ ์ง„, ์ด๊ต๊ตฌ.
    ์‹ค์–ด์ฆ ํ™˜์ž ๋Œ€์ƒ ๋””์ง€ํ„ธ ๊ธฐ์ˆ  ๊ธฐ๋ฐ˜ ์–ธ์–ด์žฌํ™œ์— ๊ด€ํ•œ ์ตœ๊ทผ ๋ฌธํ—Œ ๊ณ ์ฐฐ: VR, AR, ๋ชจ๋ฐ”์ผ ์• ํ”Œ๋ฆฌ์ผ€์ด์…˜์„ ์ค‘์‹ฌ์œผ๋กœ,
    ํ•œ๊ตญ์ฝ˜ํ…์ธ ํ•™ํšŒ๋…ผ๋ฌธ์ง€ (2022)
  • ํ—ˆ์œ ์ •, ๊น€์€์†”, ์ตœ์šฐ์„, ์˜จ๊ฒฝ์šด, ์žฅ๋ณ‘ํƒ.
    ์‹œ๊ฐ์  ๊ด€๊ณ„ ์˜ˆ์ธก์„ ์œ„ํ•œ ๊ณ„์‚ฐ ํšจ์œจ์ ์ธ ์กฐํ•ฉ์  ์ „์ด ํ‘œํ˜„ ํ•™์Šต๋ฒ•,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ ๋…ผ๋ฌธ์ง€ (2022)
  • ์ตœ์„ฑํ˜ธ, ์˜จ๊ฒฝ์šด, ํ—ˆ์œ ์ •, ์žฅ์œ ์›, ์„œ์•„์ •, ์ด์Šน์ฐฌ, ์ด๋ฏผ์ˆ˜, ์žฅ๋ณ‘ํƒ.
    DramaQA: ๊ณ„์ธต์  ์งˆ์˜์‘๋‹ต๊ณผ ํ•จ๊ป˜ํ•˜๋Š” ๋“ฑ์žฅ์ธ๋ฌผ ์ค‘์‹ฌ ๋น„๋””์˜ค ์Šคํ† ๋ฆฌ ์ดํ•ด,
    KIISE Transactions on Computing Practices (2021)

International Conference

  • S. -H. Lee, et al.
    HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised.,
    Neural Information Processing Systems (NeurIPS) (2022)

  • P. Bertens, et al.
    Emergence of Hierarchical Layers in a Single Sheet of Self-Organizing Spiking Neuron.,
    Neural Information Processing Systems (NeurIPS) (2022)

  • S. Moon, J. Lee, H. O. Song.
    Rethinking Value Function Learning for Generalization in Reinforcement Learning.,
    Neural Information Processing Systems (NeurIPS) (2022)

  • I. Hwang, et al.
    SelecMix: Debiased Learning by Contradicting-pair Sampling.,
    Neural Information Processing Systems (NeurIPS) (2022)

  • D. -S. Han, et al.
    Robust Imitation via Mirror Descent Inverse Reinforcement Learning.,
    Neural Information Processing Systems (NeurIPS) (2022)

  • W. -S. Choi, et al.
    DUEL: Adaptive Duplicate Elimination on Working Memory for Self-Supervised Learning.,
    Neural Information Processing Systems (NeurIPS) (2022)

  • S. Moon, G. An, H. O. Song.
    Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks.,
    AAAI Conference on Artificial Intelligence (AAAI) (2022)

  • J. Park, H. Shim, E. Yang
    Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation.,
    AAAI Conference on Artificial Intelligence (AAAI) (2022)

  • K. Park, H. Oh
    VECA: A New Benchmark and Toolkit for General Cognitive Development.,
    AAAI Conference on Artificial Intelligence (AAAI) (2022)

  • J. Song, J. Park, E. Yang
    TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification.,
    International Conference on Machine Learning (ICML) (2022)

  • J.-S.Kim, J.-H.Lee, B.-T.Zhang
    Smooth-Swap: A Simple Enhancement for Face-Swapping With Smoothness.,
    In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)

  • T. Vu, et al.
    SoftGroup for 3D Instance Segmentation on Point Clouds.,
    In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)

  • M. H. Ha, H. Chi, S. Chi, S. W. Lee, Q. Huang, K. Ramani
    InfoGCN: Representation Learning for Human Skeleton-based Action Recognition.,
    In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)

  • T. Kwon, M. Jeong, E. -S. Ko, Y. Lee
    Captivate! Contextual Language Guidance for Parent–Child Interaction.,
    Conference on Human Factors in Computing Systems (CHI) (2022)

  • G. -H. Lee, M. -J. Kim, M. Lee, B. -T. Zhang
    From Scratch to Sketch: Deep Decoupled Hierarchical Reinforcement Learning for Robotic Sketching Agent.,
    In Proceedings of the 2022 IEEE International Conference on Robotics and Automation (ICRA) (2022)

  • J. Park, J. Song, E. Yang

    GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification.

    International Conference on Learning Representations (ICLR) (2022)

  • S. Kim, et al.
    Few-Shot Object Detection with Proposal Balance Refinement.,
    International Conference on Pattern Recognition (ICPR) (2022)

  • M. Kang, et al.
    Grasp Planning for Occluded Objects in a Confined Space with Lateral View Using Monte Carlo Tree Search.,
    IEEE/RSJ International Conference on Intelligent Robots and Systems (2022)

  • J. G. Choy, et al.
    Unsupervised 3D Link Segmentation of Articulated Objects with a Mixture of Coherent Point Drift.,
    IEEE/RSJ International Conference on Intelligent Robots and Systems (2022)

  • T. Ha, et al.
    RIANet: Road Graph and Image Attention Network for Urban Autonomous Driving.,
    IEEE/RSJ International Conference on Intelligent Robots and Systems (2022)

  • J. RYU, M. H. Ha, S. W. Lee
    Generalizable perceptual embedding by noise-tuning alignment.,
    Organization for Computational Neurosciences (2022)

  • Y. J. Rah, S. A. Lee
    Differential effects of expectancy violation and visual salience on infants’ and toddlers’ associative learning.,
    Budapest CEU Conference on Cognitive Development (2022)

  • S. A. Lee
    Breaking the space-time continuum: How spatial boundaries structure our event memories.,
    Neuroscience 2022 (2022)

  • J. H. Shin, et al.
    In silico manipulation of human cortical computation underlying goal-directed learning.,
    Computational and Systems Neuroscience (COSYNE) (2022)

  • S. J. An, et al.
    Rethinking Tolman's latent learning with metacognitive exploration.,
    Computational and Systems Neuroscience (COSYNE) (2022)

  • S. J. An, et al.
    How human metacognitive exploration improves reinforcement learning in a sparse reward environment.,
    Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM) (2022)

  • Y. Sung, et al.
    Uncertainty and goal embeddings in the lateral prefrontal cortex guide flexible and stable reinforcement learning.,
    Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM) (2022)

  • Y. Kang, et al.
    Meta-BCI: Perspectives on a role of self-supervised learning in meta brain computer interface.,
    10th International Winter Conference on Brain-Computer Interface (BCI) (2022)

  • S. J. An, et al.
    Learning state-space uncertainty, but not value uncertainty, is sufficient for metacognitive exploration.,
    From Neuroscience to Artificially Intelligent Systems (NAISys) (2022)

  • Y. -J. Heo, E. -S. Kim, W. -S. Choi, B. -T. Zhang
    Hypergraph Transformer: Weakly-Supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering.,
    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL) (2022)

  • C. Lee, et al.
    PlaceNet: Neural Spatial Representation Learning with Multimodal Attention.,
     the 31st International Joint Conference on Artificial Intelligence (IJCAI) (2022)

  • J. H. Chai, et al.
    Mother’s initiative role in conversational exchanges and its effect on children’s language outcome.,
    The International Congress of Infant Studies (ICIS) (2022)

  • J. Jung, et al.
    The effect of socioeconomic status on early vocabulary size in South Korean children.,
    The International Congress of Infant Studies (ICIS) (2022)

  • E. -S. Ko, et al.
    Adaptation of maternal speech in statistical word segmentation of Korean.,
    The International Congress of Infant Studies (ICIS) (2022)

  • E. -S. Ko, et al.
    Korean mothers' strategies to place nouns in the utterance-final position: Comparison to American child-directed speech and Korean adult-directed speech.,
    The International Congress of Infant Studies (ICIS) (2022)

  • E. -S. Ko, et al.
    Phonological variation in child-directed speech is modulated by lexical frequency.,
    Phonological Society of Japan (PhSJ) (2022)

  • G. An, S. Moon, J.-H. Kim, H. O. Song
    Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble,
    Conference on Neural Information Processing Systems (NeurIPS) (2021)

  • K. Kim, et al.
    Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning,
    Conference on Neural Information Processing Systems (NeurIPS) (2021)

  • J. Yun, A. Lozano, E. Yang
    Adaptive Proximal Gradient Methods for Structured Neural Networks,
    Conference on Neural Information Processing Systems (NeurIPS) (2021)

  • G. Y. Park, S. W. Lee  
    Reliably Fast Adversarial Training via Latent Adversarial Perturbation,
    International Conference on Computer Vision (ICCV) (2021) (Oral Presentation)

  • G. Y. Park, S. W. Lee
    Information-theoretic regularization for Multi-source Domain Adaptation,
    International Conference on Computer Vision (ICCV) (2021)

  • G. H. Lee, S. -W. Lee
    Uncertainty-Aware Human Mesh Recovery from Video by Learning Part-Based 3D Dynamics,
    International Conference on Computer Vision (ICCV) (2021)

  • T. Kim, I. Hwang, H.-D. Lee, H. Kim, W.-S. Choi, J. Lim, B.-T. Zhang
    Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning,
    International Conference on Machine Learning (ICML) (2021)

  • W-J. Nam., J. Choi., S. -W. Lee,
    Interpreting Deep Neural Networks with Relative Sectional Propagation by Analyzing Comparative Gradients and Hostile Activations,
    AAAI Conference on Artificial Intelligence (AAAI) (2021)

  • S.-H. Lee, H.-W. Yoon, H.-R. Noh, J.-H. Kim, and S.-W. Lee,

    Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Recombination for Speech Synthesis,

    AAAI Conference on Artificial Intelligence (AAAI) (2021)

  • Y-J. Cha, S. W. Lee,

    Human Uncertainty Inference via Deterministic Ensemble Neural Networks,

    AAAI Conference on Artificial Intelligence (AAAI) (2021)

  • G. Park, J. Y. Yang., S. J. H., E. Yang.

    Attribution Preservation in Network Compression for Reliable Network Interpretation,

    Conference on Neural Information Processing Systems (NeurIPS) (2020)

  • W-J. Nam, S. Gur, J. Choi, L. Wolf, S. -W. Lee.,

    Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks,

    AAAI Conference on Artificial Intelligence (AAAI) (2020)

  • I. Chung., S. Kim., J. Lee., K. J. Kim., S. J. Hwang., E. Yang.

    Deep Mixed Effect Model using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare,

    AAAI Conference on Artificial Intelligence (AAAI) (2020)

  • J. Yi., J. Lee., K. J. Kim., S. J. Hwang., E. Yang.

    Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks,

    International Conference on Learning Representations (ICLR) (2020)

  • Y. Choi., H. Kee., K. Lee., J. Choy., J. Min., S. Lee., S. H. Oh.

    Hierarchical 6-DoF Grasping with Approaching Direction Selection,

    IEEE International Conference on Robotics and Automation (ICRA) (2020)

  • G. Lee., S. -W. Lee.

    Uncertainty-Aware Mesh Decoder for High Fidelity 3D Face Reconstruction,

    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

  • J. H. Yun., Peng Zheng, E. H. Yang., Aurelie C. Lozano, Aleksandr Aravkin,
    Trimming the L1 Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning,
    International Conference on Machine Learning (ICML) (2019). (Oral Presentation)

  • C. H. Ahn., E. W. Kim., S. H. Oh.,
    Deep Elastic Networks with Model Selection for Multi-Task Learning,
    International Conference on Computer Vision (ICCV) (2019)

  • G. H. Cha., M. S. Lee., S. H. Oh.,
    Unsupervised 3D Reconstruction Networks,
    International Conference on Computer Vision (ICCV) (2019)

  • E. S-. Ko, et al.
     Mothers’ use of tactile cues for word learning is attuned to infants’ development,
    Boston University Conference on Language Development (BUCLD46) (2021)

  • E. S-. Ko, M. McDonald
    The efficacy of book reading in infants’ word learning is mediated by child-directed speech,
    Asia Pacific Babylab Constellation (ABC) (2021)

  • E. S-. Ko, M. McDonald
    The eyes of preverbal infants reveal the effects of book reading on word learning,
    The Society for Research in Child Development (SRCD) (2021)

  • H. Kee, et al.
    Decomposed Q-learning for Non-prehensible Rearrangement Problem,
    The Inteternational Conference on Control, Automation and Systems (ICCAS) (2021)

  • A. Seo, et al.
    Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering,
    ACL-IJCNLP 2021 (2021)

  • G. -C. Kang, et al.
    Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer,
    Conference on Empirical Methods in Natural Language Processing (EMNLP) (2021)

  • B. Bebensee, 
    Co-attentional Transformers for Story-Based Video Understanding,
    International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2021)

  • J. Song, H. Shim,E. Yang
    Mutually-Constrained Monotonic Multihead Attention For Online ASR,
    International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2021)

  • J. Song, H. Shim, E. Yang
    LEARNING HOW LONG TO WAIT : ADAPTIVELY-CONSTRAINED MONOTONICMULTIHEAD ATTENTION FOR STREAMING ASR,
    IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (2021)

  • G. Park, G. Kim, E. Yang
    Distilling Linguistic Context for Language Model Compression,
    Conference on Empirical Methods in Natural Language Processing (EMNLP) (2021)

  • Y. Sung, S. W. Lee.
    Goal and context embeddings of the lateral prefrontal cortex during reinforcement learning,
    Neuroscience 2021 (2021)

  • M. R. Song, et al.
     Midbrain dopamine activity during reinforcement learning reflects bias-variance tradeoff,
    Computational and Systems Neuroscience (COSYNE) (2021)

  • D. J. Kim, S. W. Lee.
    Decoding learning strategies from EEG signals provides generalizable features for decoding decision,
    9th International Winter Conference on Brain-Computer Interface (BCI) (2021)

  • H. Joo, S. W. Lee.
    Estimating the level of inference using an order-mimic agent,
    the 6th Asian Conference on Pattern Recognition (ACPR) (2021)

  • S. J. An, S. W. Lee.
    Metacognition guides near-optimal exploration of a large state space with sparse rewards,
    Computational and Systems Neuroscience (COSYNE) (2021)

  • J. H. Shin, S. W. Lee.
    In silico manipulation of human cortical computation underlying goal-directed learning,
    Workshop on Human and Machine Decisions (WHMD) (2021)

  • S. A. Lee, 
     How Perceptual Processing of Environmental Cues Contributes to Hippocampal Memory Across Species,
    Park City Winter Conference on the Neurobiology of Learning and Memory (2021)

  • J. Park., et al.
    Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents,
    23rd ACM International Conference on Multimodal Interaction (ICMI) (2021) (Oral Presentation)

  • J. Lim., et al.
    Devil’s Advocate: Novel Boosting Ensemble Method from Psychological Findings for Text Classification,
    Conference on Empirical Methods in Natural Language Processing (EMNLP) (2021)

  • J. Lim., et al.
    Passive Versus Active: Frameworks of Active Learning for Linking Humans to Machines,
    Cognitive Science Society (CogSci) (2021)

  • N. Newcombe., A. Duval., S. A. Lee., A. Shusterman., N. Miller.

    Getting Our Bearings: Advances in Understanding Spatial Reorientation (Mapping Spatial Geometry: The Role of Vision),

    Annual Meeting of the Cognitive Science Society (CogSci) (2020).

  • Y. J. Rah., S. A. Lee.

    Effects of spatial boundary on episodic memory in children,

    Flux Congress for developmental cognitive neuroscience (2020).

  • G. Kim., H. -G. Jung., S. -W. Lee.

    Few-Shot Object Detection via Knowledge Transfer,

    IEEE International Conference on Systems, Man, and Cybernetics (2020).

  • J. Ryu., S. W. Lee.

    Brain-Like Autoencoder That Learns Latent Covariance Structure,

    From Neuroscience to Artificially Intelligent Systems (NAISys) (2020).

  • J. H. Shin., J. H. Lee., S. W. Lee.

    Deep Interaction between Reinforcement Learning Algorithms and Human Reinforcement Learning,

    From Neuroscience to Artificially Intelligent Systems (NAISys) (2020).

  • J. Park., K. Han., Y. Jeong., S. W. Lee.

    Phonemic-level duration control using attention alignment for natural speech synthesis,

    International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2020). (Oral Presentation)

  • S. Jung., J. Park., S. W. Lee.

    Polyphonic sound event detection using convolutional bidirectional LSTM and synthetic data-based transfer learning,

    International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2020).

  • M. R. Song., S. W. Lee.,
    Dynamic resource allocation during reinforcement learning accounts for ramping and phasic dopamine activity,
    Computational and Systems Neuroscience (COSYNE) (2020).
  • J. Y. Kim., Y.  J. Rah., S. A. Lee.,
    The role of spatial boundaries in episodic memory in young children,
    International Brain Research Organization (2019).
  • J. E. Hwang., J. H. Park., S. A. Lee.,

    Temporal Order Memory Performance as a Behavioral Biomarker of Alzheimer’s Disease,

    International Brain Research Organization (2019).

  • Y. J. Rah., J. H. Shin., S. A. Lee.,
    Dissociable neural signatures of prefrontal cortex for subjective and objective memory performance,
    International Brain Research Organization (2019).

  • M. J. Kang., K. J. Lee., S. H. Oh.,
    Soft Action Particle Deep Reinforcement Learning for a Continuous Action Space,
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2019).

  • Namrata Sharma., C. H. Lee., S. W. Lee.,

    Integrated Platform for Understanding Physical Prior & Task Learning,

    IEEE International Conference on Robot Intelligence Technology and Applications (2019).

  • J. H. Shin., J. H. Lee., S. Tong., S. H. Kim., S. W. Lee.,

    Designing model-based and model-free reinforcement learning tasks without human guidance,

    Multi-disciplinary Conference on Reinforcement Learning and Decision Making (2019).

  • D. J. Kim., S. W. Lee.,

    Behavioral and neural evidence for intrinsic motivation effect on reinforcement learning,

    Multi-disciplinary Conference on Reinforcement Learning and Decision Making (2019).

  • D. J. Kim., S. W. Lee.,
    Deciphering model-based and model-free reinforcement learning strategies and choices from electroencephalography,
    Multi-disciplinary Conference on Reinforcement Learning and Decision Making (2019).
  • S. J. An, B. D. Martino, and S. W. Lee.,

    Metacognitive exploration in reinforcement learning,

    Multi-disciplinary Conference on Reinforcement Learning and Decision Making (2019).

  • Y.  J. Rah., J. H. Shin., S. A. Lee.,
    Predicting subjective and objective memory recollection from prefrontal cortex activations using high-density fNIRS,
    Neuroscience (2019).

  • J. H. Shin., S. A. Lee.,

    Neural representation of episodic memory components in the prefrontal cortex measured by fNIRS,

    Neuroscience (2019). (Oral Presentation)

  • S. A. Lee.

    The binding of space and time in episodic memory,

    Flux Congress for developmental cognitive neuroscience (2019).

  • S. A. Lee.

    Spatiotemporal binding in episodic memory,

    Hippocampus symposium (2019).

  • J. H. Shin., J. H. Lee., S. Tong., S. H. Kim., S. W. Lee.,

    Designing model-based and model-free reinforcement learning tasks without human guidance,

    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2019).

Domestic Conference

  • ์ตœ์›์„, et al.
    ๋ถ€๋ถ„์  ๊ด€์ธก ๊ฐ€๋Šฅ ํ™˜๊ฒฝ์—์„œ์˜ ๊ฐ์ฒด ์ธ์‹์„ ์œ„ํ•œ ์ž๊ธฐ ์ง€๋„ ํ•™์Šต ์•Œ๊ณ ๋ฆฌ์ฆ˜,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ๋ฐ•์˜ˆ์†”, et al.
    CycleGAN์„ ์ด์šฉํ•œ ์‹ค๋‚ด ์ €์กฐ๋„ ์•ผ๊ฐ„ ํ™˜๊ฒฝ์—์„œ์˜ ๊ฐ์ฒด ๊ฒ€์ถœ,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ๋ฐ•์ค€์„, et al.
    ๊ฒฐ์ •์  ์‹œ๊ธฐ๋ฅผ ํ™œ์šฉํ•œ ์•ˆํ‹ฐ ์ปค๋ฆฌํ˜๋Ÿผ ๊ฐ•ํ™”ํ•™์Šต,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ๊น€๊ธฐ๋ฒ”, et al.
    ๋‹ค์ค‘ ๋ชฉํ‘œ ๊ฐ•ํ™”ํ•™์Šต์—์„œ ๋ถˆ๊ท ํ˜• ๋ฌธ์ œ๋ฅผ ์œ„ํ•œ ๊ท ๋“ฑ ์ƒ˜ํ”Œ๋ง ๋ฐฉ๋ฒ•,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ์ •์„ฑ์ค€, et al.
    ๋‹ค์ค‘์–ธ์–ด ํ…์ŠคํŠธ-์ด๋ฏธ์ง€ ์ƒ์„ฑ,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ์ด์ƒ์ค€, et al.
    ๋ถ„๋ฅ˜ ๋ชจ๋ธ์˜ ๊ฐ•๊ฑด์„ฑ ์ฆ๋Œ€๋ฅผ ์œ„ํ•œ ํ˜•ํƒœ ์ค‘์‹ฌ ๋ฐ์ดํ„ฐ ์ฆ๊ฐ• ์ ์šฉ,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ํ—ˆ์œ ์ •, et al.
    ์‚ฌ์šฉ์ž ์ผ์ƒ ํ•™์Šต ๋ชจ๋ธ์˜ ์˜ˆ์ธก ๋ถˆํ™•์‹ค์„ฑ์— ๊ธฐ๋ฐ˜ํ•œ ๋น„์ผ์ƒ ์ด๋ฒคํŠธ ํƒ์ง€ ๊ธฐ์ˆ ,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ์†ก์—ฐ์ง€, et al.
    ์ƒํ˜ธ์ •๋ณด๋Ÿ‰ ๊ธฐ๋ฐ˜ ์ž๊ธฐ์ง€๋„ ๋‹ค์ค‘ ๊ฐ์ฒด ๊ฐ•ํ™”ํ•™์Šต,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ์ด๊ฐ•ํ›ˆ, et al.
    ์‹ฌ์ธต ๊ฐ•ํ™”ํ•™์Šต ๊ธฐ๋ฐ˜์˜ ์ŠคํŠธ๋กœํฌ-์กฐ๊ฑดํ™”๋œ ์ž๋™ ํŽ˜์ธํŒ…,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ๊ฐ•๊ธฐ์ฒœ, et al.
    ์ž๋™ ํšŒ๊ท€ ๊ธฐ๋ฐ˜ ์‹œ๊ฐ ๋Œ€ํ™” ์ƒ์„ฑ ๊ธฐ๋ฒ•,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ์ž„์Šนํ˜„, et al.
    ์žฅ์• ๋ฌผ ํšŒํ”ผ ๋ฐ ์ œ๊ฑฐ๋ฅผ ๊ณ ๋ คํ•œ ์ด๋™ํ˜• ์กฐ์ž‘ ๋กœ๋ด‡์˜ ์‹ค๋‚ด ๊ฒฝ๋กœ ํ”Œ๋ž˜๋„ˆ,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ๊ณฝ์œคํ˜, et al.
    ์ ์‘ํ˜• Neural ODE๋ฅผ ํ™œ์šฉํ•œ ํšจ์œจ์ ์ธ ์˜คํ”„๋ผ์ธ ๊ฐ•ํ™”ํ•™์Šต,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ์„คํ•œ์šธ, et al.
    ์ง€๋„ํ•™์Šต ๋ฐ์ดํ„ฐ๊ฐ€ ์ ์€ ํ™˜๊ฒฝ์—์„œ ๊ฐ•๊ฑดํ•œ ์ง€์นญ ํ‘œํ˜„ ์„ธ๊ทธ๋ฉ˜ํ…Œ์ด์…˜ ํ•™์Šต,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ๊น€์ •ํ˜„, et al.
    ์ง€์นญ ํ‘œํ˜„ ์„ธ๊ทธ๋ฉ˜ํ…Œ์ด์…˜์„ ์œ„ํ•œ ์–ดํ…์…˜ ๊ธฐ๋ฐ˜ ํ…์ŠคํŠธ ์ฆ๊ฐ• ๊ธฐ๋ฒ•,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ์ „์ˆ˜์ง„, et al.
    ํˆฌ๋ช…์„ฑ ํƒ์ง€ ํ•™์Šต์„ ์œ„ํ•œ ๋น„์ง€๋„ ํ•™์Šต ๊ธฐ๋ฐ˜ ๋ฐ์ดํ„ฐ ์ƒ์„ฑ ์‹œ์Šคํ…œ,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ํ™ฉ์ธ์šฐ, et al.
    ํŽธํ–ฅ๋œ ๋ฐ์ดํ„ฐ์…‹์—์„œ์˜ ๋ฐ์ดํ„ฐ ์ฆ๊ฐ•์˜ ํšจ๊ณผ์— ๋Œ€ํ•œ ๊ณ ์ฐฐ,
    ํ•œ๊ตญ์ •๋ณด๊ณผํ•™ํšŒ 2022 ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2022)

  • ๊น€ํฌ์ค€, et al.
    Hippocampal Successor Representation Learning for Zero-shot Navigation,
    ํ•œ๊ตญ์ธ๊ณต์ง€๋Šฅํ•™ํšŒ ํ•˜๊ณ„ํ•™์ˆ ๋Œ€ํšŒ (2022)

  • E. S-. Ko, et al.
    An acoustic study of Korean mothers` vowel space,
    ํ•œ๊ตญ์Œ์„ฑํ•™ํšŒ (2021)

  • E. S-. Ko,
    How we talk to infants and why it matters: Insights from Korean infants and their caregivers ,
    ํ•œ๊ตญ์–ธ์–ดํ•™ํšŒ (2021)

  • B.Bebensee, et al.
    Exploring bias and its effects in the DramaQA dataset in video question answering,
    2021 ํ•œ๊ตญ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2021)

  • ์ด๊ฐ•ํ›ˆ, et al.
    ํ•œ๋ถ“ ๋”ฐ๋ผ๊ทธ๋ฆฌ๊ธฐ๋ฅผ ์œ„ํ•œ ๋ชจ๋ธ ๊ธฐ๋ฐ˜ ์ปค๋ฆฌํ˜๋Ÿผ ๊ฐ•ํ™”ํ•™์Šต,
    2021 ํ•œ๊ตญ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2021)

  • ๊น€์ค€ํ˜ธ, et al.
    Learning to Avoid Obstacles by Fast-Adapting Parameters to New Environments,
    2021 ํ•œ๊ตญ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2021)

  • ๊น€๋ฏผ์ง€, et al.
    ๋กœ๋ด‡ ์กฐ์ž‘๊ธฐ์ˆ  ํ•™์Šต์„ ์œ„ํ•œ ๋ฆฌ์…‹ํ”„๋ฆฌ ๊ฒฝ์Ÿ์  ๊ฐ•ํ™”ํ•™์Šต,
    2021 ํ•œ๊ตญ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2021)

  • ์†ก์—ฐ์ง€, et al.
    ์‹ฌ์ธต ๊ฐ•ํ™”ํ•™์Šต์„ ์ด์šฉํ•œ ์ด๋™ ์žฅ์• ๋ฌผ ํšŒํ”ผ ๋ฐ ์ตœ์  ๊ฒฝ๋กœ ํƒ์ƒ‰ ๊ธฐ๋ฒ•,
    2021 ํ•œ๊ตญ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2021)

  • ์ด๊ฐ•ํ›ˆ, et al.
    ๋ถ„๊ธฐ๋œ ์ผํ™”๊ธฐ์–ต ๊ธฐ๋ฐ˜์˜ ์ž๊ธฐ์ง€๋„์  ์ •์ฑ… ํ•™์Šต ๋ฐฉ๋ฒ•,
    2021 ํ•œ๊ตญ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2021)

  • ์ด์ƒ์ค€, et al.
    ์›์ƒท ๋ฌผ์ฒด ํƒ์ง€๋ฅผ ์ด์šฉํ•œ ์ด๋™ํ˜• ๋กœ๋ด‡์˜ ์„œ๋น„์Šค ์‘์šฉ ๋ฐฉ๋ฒ•,
    2021 ํ•œ๊ตญ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2021)

  • ๊น€ํ˜„์„œ, et al.
    ๊ต์ฐจ ๋„๋ฉ”์ธ์—์„œ์˜ ํ–‰๋™ ์˜ˆ์ธก์„ ์œ„ํ•œ ๋ฏธ๋ž˜ ์ƒํƒœ ์ƒ์„ฑ ๋ฐฉ๋ฒ•,
    2021 ํ•œ๊ตญ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2021)

  • ์ตœ์„ฑํ˜ธ, et al.
    ๋‹ค์ˆ˜์ค€ ๋“ฑ์žฅ์ธ๋ฌผ ์ฃผ์˜์ง‘์ค‘์„ ํ†ตํ•œ ๋น„๋””์˜ค ์Šคํ† ๋ฆฌ ์ดํ•ด ๊ธฐ๋ฒ•,
    2021 ํ•œ๊ตญ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2021)

  • ์„œ์•„์ •, et al.
    ๋น„๋””์˜ค ์งˆ์˜์‘๋‹ต์„ ์œ„ํ•œ ๋™์ž‘-๋ชจ์–‘ ์ฃผ์˜์ง‘์ค‘ ๋„คํŠธ์›Œํฌ,
    2021 ํ•œ๊ตญ์ปดํ“จํ„ฐ์ข…ํ•ฉํ•™์ˆ ๋Œ€ํšŒ (2021)

  • E. S-. Ko
    Not All Input is Equal: The Efficacy of Book Reading in Infants’ Word Learning is Mediated by Child-Directed Speech,
    ํ•œ๊ตญ์–ธ์–ดํ•™ํšŒ ์—ฌ๋ฆ„ํ•™์ˆ ๋Œ€ํšŒ (2021)

  • M. R. Song., S. W. Lee.

    Midbrain dopamine activity during reinforcement learning reflects bias-variance tradeoff,

    ํ•œ๊ตญ์ธ๊ณต์ง€๋Šฅํ•™ํšŒ ํ•˜๊ณ„ํ•™์ˆ ๋Œ€ํšŒ (2020).

  • M. Yang., J. H. Lee, S. W. Lee.

    Biological Reinforcement Learning via Predictive Spacetime Encoding,

    ํ•œ๊ตญ์ธ๊ณต์ง€๋Šฅํ•™ํšŒ ํ•˜๊ณ„ํ•™์ˆ ๋Œ€ํšŒ (2020).

  • J. H. Shin., J. H. Lee., S. W. Lee.

    Deep Interaction between Reinforcement Learning Algorithms and Human Reinforcement Learning,

    ํ•œ๊ตญ์ธ๊ณต์ง€๋Šฅํ•™ํšŒ ํ•˜๊ณ„ํ•™์ˆ ๋Œ€ํšŒ (2020).

  • H. Kee., C. Ahn., S. H. Oh.

    Model selection for imitation learning,

    ํ•œ๊ตญ์ธ๊ณต์ง€๋Šฅํ•™ํšŒ ํ•˜๊ณ„ํ•™์ˆ ๋Œ€ํšŒ (2020).

  • J. Park, J. G. Choy., S. H. Oh.

    Memory Efficient Reinforcement Learning for Multi-tasks with Deep Virtual Q-Networks,

    ํ•œ๊ตญ์ธ๊ณต์ง€๋Šฅํ•™ํšŒ ํ•˜๊ณ„ํ•™์ˆ ๋Œ€ํšŒ (2020).

  • N. Kim., S. H. Oh.

    Active Multi-Class Object Detection Using Deep Reinforcement Learning,

    ํ•œ๊ตญ์ธ๊ณต์ง€๋Šฅํ•™ํšŒ ํ•˜๊ณ„ํ•™์ˆ ๋Œ€ํšŒ (2020).

  • J. Y. Kim., Y.  J. Rah., S. A. Lee.

    ๊ณต๊ฐ„์—์„œ์˜ ๊ฒฝ๊ณ„๊ฐ€ ์•„๋™์˜ ์ผํ™” ๊ธฐ์–ต์— ๋ฏธ์น˜๋Š” ์˜ํ–ฅ(How spatial boundaries influence children’s episodic memory),

    ํ•œ๊ตญ์ธ์ง€๋ฐ์ƒ๋ฌผ์‹ฌ๋ฆฌํ•™ํšŒ (2020).

  • S. A. Lee.

    How the Brain Represents Spatiotemporal Events,

    ํ•œ๊ตญ์ธ์ง€๋ฐ์ƒ๋ฌผ์‹ฌ๋ฆฌํ•™ํšŒ (2020).

  • S. A. Lee.

    Leveraging the Interaction Between Attention and Affect,

    ํ•œ๊ตญ์ž„์ƒ์‹ฌ๋ฆฌํ•™ํšŒ ๊ฐ€์„ํ•™์ˆ ๋Œ€ํšŒ (2020).

  • S. A. Lee., S. Park.

    Investigating Age-Related Decline and Compensation in Hippocampal Memory Processes Using Human Intracranial EEG,

    ๋Œ€ํ•œ๋‡Œ๊ธฐ๋Šฅ๋งคํ•‘ํ•™ํšŒ ์ถ”๊ณ„ํ•™์ˆ ๋Œ€ํšŒ (2020).

  • J. H. Shin., S. A. Lee.,

    Novelty and uncertainty representation in the human brain during flexible learning,

    ํ•œ๊ตญ์ธ์ง€๊ณผํ•™ํšŒ ํ•™์ˆ ๋Œ€ํšŒ (2019).

  • H. Y. Yoo., E. W. Kim., S. H. Oh.,
    ์ค‘์ฒฉ ํฌ์†Œ ๋„คํŠธ์›Œํฌ๋ฅผ ์ด์šฉํ•œ ๊ณ„์ธต์ ์ธ ์ด๋ฏธ์ง€ ์˜๋ฏธ๋ก ์  ๋ถ„ํ•  ๋„คํŠธ์›Œํฌ,
    ํ†ต์‹ ์ •๋ณด ํ•ฉ๋™ํ•™์ˆ ๋Œ€ํšŒ (2019).

  • J. E. Hwang., S. A. Lee.,
    Development of what, where, when components in episodic memory,
    ํ•œ๊ตญ์ธ์ง€๊ณผํ•™ํšŒ (2019).

  • Gitae Koo., S. A. Lee.,
    Scene perception and memory: Comparison of Scene Memory Performance in Williams Syndrome and Typical Young Adults,
    ํ•œ๊ตญ์ธ์ง€๊ณผํ•™ํšŒ (2019).

  • J. H. Shin., S. A. Lee.,
    Novelty and uncertainty representation in the human brain during flexible learning,
    ํ•œ๊ตญ์ธ์ง€๊ณผํ•™ํšŒ (2019).

  • Y.  J. Rah., S. A. Lee.,
    The contrast between subjective and objective memory in recalling events with episodic memory components.
    ํ•œ๊ตญ์ธ์ง€๊ณผํ•™ํšŒ (2019).

  • S. A. Lee.

    Spatial cognition and episodic memory in childhood,

    ํ•œ๊ตญ์ƒ์• ํ•™ํšŒ (2019).

  • Y. J. Rah., S. A. Lee.,
    ๊ธฐ์–ต๋ฐœ๋‹ฌ๊ณผ ๊ณต๊ฐ„์ธ์ง€ (Development of Spatial Cognition and Episodic Memory).
    ์ธ์ง€๋ฐœ๋‹ฌ์ค‘์žฌํ•™ํšŒ ๋™๊ณ„ํ•™์ˆ ๋Œ€ํšŒ (2019).

International Collaboration

  • (KAIST-IBM) J. Yun, A. Lozano, E. Yang
    Adaptive Proximal Gradient Methods for Structured Neural Networks,
    Conference on Neural Information Processing Systems (NeurIPS) (2021)

  • (Chosun Univeristy-University of Ottawa) E. S-. Ko, M. McDonald
    The efficacy of book reading in infants’ word learning is mediated by child-directed speech,
    Asia Pacific Babylab Constellation (ABC) (2021)

  • (Chosun Univeristy-University of Ottawa)  E. S-. Ko, M. McDonald
    The eyes of preverbal infants reveal the effects of book reading on word learning,
    The Society for Research in Child Development (SRCD) (2021)

  • (Chosun Univeristy-The University of Plymouth-Purdue University)  E. S-. Ko, et al.
     Mothers’ use of tactile cues for word learning is attuned to infants’ development,
    Boston University Conference on Language Development (BUCLD46) (2021)

  • (KAIST-Caltech) Kim, D., Park, G. Y., O’Doherty J. P.*, Lee S. W.*

    Task complexity interacts with state-space uncertainty in the arbitration process between model-based and model-free reinforcement-learning at both behavioral and neural levels.

    Nature Communications. 10, 5738 (2019).

  • (KAIST-Caltech) O’Doherty J. P.*, Lee S. W., TadayonNejad R., Cockburn J., Iigaya K., Chrpentier C.

    Why and how the brain weights contributions from a mixture of experts.

    Neuroscience and Biobehavioral Reviews (2020)

  • (KAIST-NYU Shanghai) Zuo, S., Wang, L., Shin, J. H., Cai, Y., Lee, S. W., Appiah, K., Zhou, Y., Kwok S. C.

    Behavioral evidence for memory replay of video episodes in the macaque.

    eLife. 9, e54519 (2020).

  • (KAIST-U Zurich) Weissengruber S.+, Lee S. W.+, O'Doherty J, Ruff C.

    Neurostimulation reveals context-dependent arbitration between model-based and model-free learning.

    Cerebral Cortex. 29 (2019).

  • (KAIST-UCL) S. J. An, B. D. Martino, and S. W. Lee*

    Metacognitive exploration in reinforcement learning.

    4th Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM) (2019).

  • (KAIST-IBM) J. Yun, P. Zheng, A. Lozano, A. Aravkin and E. Yang

    Trimming the l-1 Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning.

    International Conference on Machine Learning (ICML) 36 (2019) (Oral, acceptance rate = 4.64%) .

  • (KAIST-IBM) J. Yun, A. Lozano and E. Yang

    Stochastic Gradient Methods with Block Diagonal Matrix Adaptation.

    arXiv preprint arXiv:1905.10757 (2019).

  • (KAIST-IBM) J. Yun, A. Lozano, E. Yang

    A General Family of Stochastic Proximal Gradient Methods for Deep Learning.

    arXiv preprint arXiv:2007.07484 (2020).

  • (๊ณ ๋ ค๋Œ€-Technische Universität Berlin) D.-O. Won, K.-R. Müller, and S.-W. Lee

    An adaptive deep reinforcement learning framework enables curling robots with human-like performance in real world conditions.

    Science Robotics. Vol. 5, Issue 46 (2020).

  • (KAIST-Columnbia) Sang-Eon Park, Tamara Gedankein, Joshua Jacobs, Sang Ah Lee

    What human intracranial EEG reveals about the effects of aging on neurocognitive function.

    ํ•œ๊ตญ๋‡Œ์‹ ๊ฒฝ๊ณผํ•™ํšŒ (2020)

Domestic Collaboration

  • (KAIST-Humelo) B.-J. Choi, J. Hong, D. Park and S. W. Lee

    F^2-Softmax: Diversifying Neural Text Generation via Frequency Factorized Softmax.

    Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020) (acceptance rate = 22.4%)

  • (KAIST-Humelo) M. Elgaar, J. Park, and S. W. Lee*

    Multi-speaker and multi-domain emotional voice conversion using factorized hierarchical variational autoencoder.

    Proceeding of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2020)

  • (KAIST-Humelo) J. Park, K. Han, Y. Jeong, and S. W. Lee*

    Phonemic-level duration control using attention alignment for natural speech synthesis.

    Proceeding of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2019) (Oral)

  • (KAIST-Humelo) S. Jung, J. Park, and S. W. Lee*

    Polyphonic sound event detection using convolutional bidirectional LSTM and synthetic data-based transfer learning.

    Proceeding of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2019)

  • (KAIST-KAIST) Junghan Shin, Suyeon Heo, Sang Ah Lee, Sang Wan Lee

    Novelty and uncertainty representation in the human brain during flexible learning.

    ํ•œ๊ตญ์ธ์ง€๊ณผํ•™ํšŒ (2019)

  • (KAIST-KAIST) S. A. Lee, S. W. Lee

    ์ธ๊ฐ„์ง€๋Šฅ, ์ธ๊ณต์ง€๋Šฅ.

    ํ•œ๊ตญ์ธ์ง€๊ณผํ•™ํšŒ (2019)