Will Grathwohl

Publication Activity (10 Years)

Years Active: 2016-2023
Publications (10 Years): 25

Top Topics

Diffusion Model

Gradient Estimation

Text Generation

Importance Sampling

Top Venues

Publications

Yilun Du, Conor Durkan, Robin Strudel, Joshua B. Tenenbaum, Sander Dieleman, Rob Fergus, Jascha Sohl-Dickstein, Arnaud Doucet, Will Grathwohl
Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC. CoRR (2023)
Francisco Vargas, Will Grathwohl, Arnaud Doucet
Denoising Diffusion Samplers. CoRR (2023)
Katayoon Goshvadi, Haoran Sun, Xingchao Liu, Azade Nova, Ruqi Zhang, Will Grathwohl, Dale Schuurmans, Hanjun Dai
DISCS: A Benchmark for Discrete Sampling. NeurIPS (2023)
Arnaud Doucet, Will Grathwohl, Alexander G. de G. Matthews, Heiko Strathmann
Score-Based Diffusion meets Annealed Importance Sampling. CoRR (2022)
Sander Dieleman, Laurent Sartran, Arman Roshannai, Nikolay Savinov, Yaroslav Ganin, Pierre H. Richemond, Arnaud Doucet, Robin Strudel, Chris Dyer, Conor Durkan, Curtis Hawthorne, Rémi Leblond, Will Grathwohl, Jonas Adler
Continuous diffusion for categorical data. CoRR (2022)
Manzil Zaheer, Kenneth Marino, Will Grathwohl, John Schultz, Wendy Shang, Sheila Babayan, Arun Ahuja, Ishita Dasgupta, Christine Kaeser-Chen, Rob Fergus
Learning to Navigate Wikipedia by Taking Random Walks. NeurIPS (2022)
Robin Strudel, Corentin Tallec, Florent Altché, Yilun Du, Yaroslav Ganin, Arthur Mensch, Will Grathwohl, Nikolay Savinov, Sander Dieleman, Laurent Sifre, Rémi Leblond
Self-conditioned Embedding Diffusion for Text Generation. CoRR (2022)
Arnaud Doucet, Will Grathwohl, Alexander G. de G. Matthews, Heiko Strathmann
Score-Based Diffusion meets Annealed Importance Sampling. NeurIPS (2022)
Manzil Zaheer, Kenneth Marino, Will Grathwohl, John Schultz, Wendy Shang, Sheila Babayan, Arun Ahuja, Ishita Dasgupta, Christine Kaeser-Chen, Rob Fergus
Learning to Navigate Wikipedia by Taking Random Walks. CoRR (2022)
Jacob Kelly, Richard S. Zemel, Will Grathwohl
Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data. CoRR (2021)
Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud, Chris J. Maddison
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions. CoRR (2021)
Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud, Chris J. Maddison
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions. ICML (2021)
Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Mohammad Norouzi, Kevin Swersky
Your classifier is secretly an energy based model and you should treat it like one. ICLR (2020)
Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Richard S. Zemel
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling. ICML (2020)
Ethan Fetaya, Jörn-Henrik Jacobsen, Will Grathwohl, Richard S. Zemel
Understanding the Limitations of Conditional Generative Models. ICLR (2020)
Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Richard S. Zemel
Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling. CoRR (2020)
Will Grathwohl, Jacob Kelly, Milad Hashemi, Mohammad Norouzi, Kevin Swersky, David Duvenaud
No MCMC for me: Amortized sampling for fast and stable training of energy-based models. CoRR (2020)
Jens Behrmann, Will Grathwohl, Ricky T. Q. Chen, David Duvenaud, Jörn-Henrik Jacobsen
Invertible Residual Networks. ICML (2019)
Will Grathwohl, Ricky T. Q. Chen, Jesse Bettencourt, Ilya Sutskever, David Duvenaud
FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models. ICLR (2019)
Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Mohammad Norouzi, Kevin Swersky
Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One. CoRR (2019)
Will Grathwohl, Ricky T. Q. Chen, Jesse Bettencourt, Ilya Sutskever, David Duvenaud
FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models. CoRR (2018)
Will Grathwohl, Elliot Creager, Seyed Kamyar Seyed Ghasemipour, Richard S. Zemel
Gradient-based Optimization of Neural Network Architecture. ICLR (Workshop) (2018)
Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, David Duvenaud
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation. ICLR (Poster) (2018)
Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, David Duvenaud
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation. CoRR (2017)
Will Grathwohl, Aaron Wilson
Disentangling Space and Time in Video with Hierarchical Variational Auto-encoders. CoRR (2016)