Recent Publications

  • In defense of dual-encoders for neural ranking, ICML 2022
    Aditya Krishna Menon, Sadeep Jayasumana, Seungyeon Kim, Ankit Singh Rawat, Sashank J Reddi, Sanjiv Kumar

  • A statistical perspective on distillation, ICML 2021
    Aditya K Menon, Ankit Singh Rawat, Sashank Reddi, Seungyeon Kim, Sanjiv Kumar

  • Rankdistil: Knowledge distillation for ranking, AISTATS 2021
    Sashank Reddi, Rama Kumar Pasumarthi, Aditya Menon, Ankit Singh Rawat, Felix Yu, Seungyeon Kim, Andreas Veit, Sanjiv Kumar

  • Evaluations and methods for explanation through robustness analysis, ICLR 2021
    Cheng-Yu Hsieh, Chih-Kuan Yeh, Xuanqing Liu, Pradeep Ravikumar, Seungyeon Kim, Sanjiv Kumar, Cho-Jui Hsieh

  • Semantic label smoothing for sequence to sequence problems, EMNLP 2020
    Michal Lukasik, Himanshu Jain, Aditya Krishna Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix Yu, Sanjiv Kumar

  • Why are adaptive methods good for attention models? NeurIPS 2020
    Jingzhao Zhang, Sai Praneeth Karimireddy, Andreas Veit, Seungyeon Kim, Sashank Reddi, Sanjiv Kumar, Suvrit Sra

Book

  • Your first machine learning rook (처음 배우는 머신러닝), Hanbit Publishing Network 2017.
    Seungyeon Kim and Youngjoo Chung,

Recent Preprints

  • Teacher Guided Training: An Efficient Framework for Knowledge Transfer, 2022
    Manzil Zaheer, Ankit Singh Rawat, Seungyeon Kim, Chong You, Himanshu Jain, Andreas Veit, Rob Fergus, Sanjiv Kumar

  • Balancing robustness and sensitivity using feature contrastive learning, 2021
    Seungyeon Kim, Daniel Glasner, Srikumar Ramalingam, Cho-Jui Hsieh, Kishore Papineni, Sanjiv Kumar

  • On the reproducibility of neural network predictions, 2021
    Srinadh Bhojanapalli, Kimberly Wilber, Andreas Veit, Ankit Singh Rawat, Seungyeon Kim, Aditya Menon, Sanjiv Kumar