Kevin Clark

I am an AI researcher with experience across pre-training, post-training, and generative modeling at Google DeepMind and Google Brain. I obtained my PhD from Stanford's Natural Language Processing Group advised by Chris Manning.

Email: kevinclark425(at)gmail.com
[CV] [github] [google scholar]

Publications

  • Directly Fine-Tuning Diffusion Models on Differentiable Rewards
    Kevin Clark, Paul Vicol, Kevin Swersky, and David J Fleet
    International Conference on Learning Representations (ICLR), 2024.
    [paper]
  • Intriguing Properties of Generative Classifiers
    Priyank Jaini, Kevin Clark, and Robert Geirhos
    International Conference on Learning Representations (ICLR), 2024.
    [paper]
  • Text-to-Image Diffusion Models are Zero-Shot Classifiers
    Kevin Clark and Priyank Jaini
    Neural Information Processing Systems (NeurIPS), 2023.
    [paper]
  • Towards Expert-Level Medical Question Answering with Large Language Models
    Karan Singhal, Tao Tu, Juraj Gottweis, Rory Sayres, Ellery Wulczyn, Le Hou, Kevin Clark, Stephen Pfohl, Heather Cole-Lewis, Darlene Neal, Mike Schaekermann, Amy Wang, Mohamed Amin, Sami Lachgar, Philip Mansfield, Sushant Prakash, Bradley Green, Ewa Dominowska, Blaise Aguera y Arcas, Nenad Tomasev, Yun Liu, Renee Wong, Christopher Semturs, S. Sara Mahdavi, Joelle Barral, Dale Webster, Greg S. Corrado, Yossi Matias, Shekoofeh Azizi, Alan Karthikesalingam, and Vivek Natarajan
    Nature Medicine, 2023.
    [paper]
  • Meta-Learning Fast Weight Language Models
    Kevin Clark, Kelvin Guu, Ming-Wei Chang, Panupong Pasupat, Geoffrey Hinton, and Mohammad Norouzi
    Empirical Methods in Natural Language Processing (EMNLP), 2022.
    [paper] [code]
  • Pre-Training Transformers as Energy-Based Cloze Models
    Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning.
    Empirical Methods in Natural Language Processing (EMNLP), 2020.
    [paper] [code]
  • Emergent linguistic structure in artificial neural networks trained by self-supervision
    Christopher D. Manning, Kevin Clark, John Hewitt, Urvashi Khandelwal, and Omer Levy
    Proceedings of the National Academy of Sciences, 2020.
    [paper]
  • ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
    Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning.
    International Conference on Learning Representations (ICLR), 2020.
    [paper] [code]
  • What Does BERT Look At? An Analysis of BERT's Attention.
    Kevin Clark, Urvashi Khandelwal, Omer Levy, and Christopher D. Manning.
    BlackBoxNLP@ACL, 2019, Best Paper Award
    [paper] [code]
  • BAM! Born-Again Multi-Task Networks for Natural Language Understanding.
    Kevin Clark, Minh-Thang Luong, Urvashi Khandelwal, Christopher D. Manning, and Quoc V. Le.
    Association for Computational Linguistics (ACL), 2019.
    [paper] [code]
  • Semi-Supervised Sequence Modeling with Cross-View Training.
    Kevin Clark, Minh-Thang Luong, Christopher D. Manning, and Quoc V. Le.
    Empirical Methods in Natural Language Processing (EMNLP), 2018.
    [paper] [code]
  • Deep Reinforcement Learning for Mention-Ranking Coreference Models.
    Kevin Clark and Christopher D. Manning.
    Empirical Methods in Natural Language Processing (EMNLP), 2016.
    [paper] [code]
  • Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora.
    William L. Hamilton, Kevin Clark, Jure Leskovec, and Dan Jurafsky.
    Empirical Methods in Natural Language Processing (EMNLP), 2016.
    [paper] [project website (code + data)]
  • Improving Coreference Resolution by Learning Entity-Level Distributed Representations.
    Kevin Clark and Christopher D. Manning.
    Association for Computational Linguistics (ACL), 2016.
    [paper] [code]
  • Large-scale Analysis of Counseling Conversations: An Application of Natural Language Processing to Mental Health
    Tim Althoff, Kevin Clark, and Jure Leskovec.
    Transactions of the Association for Computational Linguistics (TACL), 2016.
    [paper] [project website] [dataset]
  • Entity-Centric Coreference Resolution with Model Stacking.
    Kevin Clark and Christopher D. Manning.
    Association for Computational Linguistics (ACL), 2015.
    [paper] [code]
  • RevMiner: an Extractive Interface for Navigating Reviews on a Smartphone.
    Jeff Huang, Oren Etzioni, Luke Zettlemoyer, Kevin Clark, and Christian Lee.
    User Interface Software and Technology (UIST), 2012.
    [paper]

Other Projects