Will Grathwohl

28 papers A* 8Journal 16Unranked 3

Year	Rank	Type	Title / Venue / Authors
2024	J	`jnl`	A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks. CoRR Nicholas Monath, Will Grathwohl, Michael Boratko, Rob Fergus, Andrew McCallum, Manzil Zaheer
2024	J	`jnl`	Variance reduction of diffusion model's gradients with Taylor approximation-based control variate. CoRR Paul Jeha, Will Grathwohl, Michael Riis Andersen, Carl Henrik Ek, Jes Frellsen
2023	A*	`conf`	DISCS: A Benchmark for Discrete Sampling. NeurIPS Katayoon Goshvadi, Haoran Sun, Xingchao Liu, Azade Nova, Ruqi Zhang, Will Grathwohl, Dale Schuurmans, Hanjun Dai
2023	J	`jnl`	Denoising Diffusion Samplers. CoRR Francisco Vargas, Will Grathwohl, Arnaud Doucet
2023	J	`jnl`	Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC. CoRR Yilun Du, Conor Durkan, Robin Strudel, Joshua B. Tenenbaum, Sander Dieleman, Rob Fergus, Jascha Sohl-Dickstein, Arnaud Doucet, Will Grathwohl
2022	J	`jnl`	Continuous diffusion for categorical data. CoRR 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
2022	A*	`conf`	Learning to Navigate Wikipedia by Taking Random Walks. NeurIPS Manzil Zaheer, Kenneth Marino, Will Grathwohl, John Schultz, Wendy Shang, Sheila Babayan, Arun Ahuja, Ishita Dasgupta, Christine Kaeser-Chen, Rob Fergus
2022	J	`jnl`	Learning to Navigate Wikipedia by Taking Random Walks. CoRR Manzil Zaheer, Kenneth Marino, Will Grathwohl, John Schultz, Wendy Shang, Sheila Babayan, Arun Ahuja, Ishita Dasgupta, Christine Kaeser-Chen, Rob Fergus
2022	A*	`conf`	Score-Based Diffusion meets Annealed Importance Sampling. NeurIPS Arnaud Doucet, Will Grathwohl, Alexander G. de G. Matthews, Heiko Strathmann
2022	J	`jnl`	Score-Based Diffusion meets Annealed Importance Sampling. CoRR Arnaud Doucet, Will Grathwohl, Alexander G. de G. Matthews, Heiko Strathmann
2022	J	`jnl`	Self-conditioned Embedding Diffusion for Text Generation. CoRR Robin Strudel, Corentin Tallec, Florent Altché, Yilun Du, Yaroslav Ganin, Arthur Mensch, Will Grathwohl, Nikolay Savinov, Sander Dieleman, Laurent Sifre, Rémi Leblond
2021	—	`—`	Applications and Methods for Energy-based Models at Scale. Will Grathwohl
2021	J	`jnl`	Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data. CoRR Jacob Kelly, Richard S. Zemel, Will Grathwohl
2021	A*	`conf`	Oops I Took A Gradient: Scalable Sampling for Discrete Distributions. ICML Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud, Chris J. Maddison
2021	J	`jnl`	Oops I Took A Gradient: Scalable Sampling for Discrete Distributions. CoRR Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud, Chris J. Maddison
2020	J	`jnl`	Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling. CoRR Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Richard S. Zemel
2020	A*	`conf`	Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling. ICML Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Richard S. Zemel
2020	J	`jnl`	No MCMC for me: Amortized sampling for fast and stable training of energy-based models. CoRR Will Grathwohl, Jacob Kelly, Milad Hashemi, Mohammad Norouzi, Kevin Swersky, David Duvenaud
2020	A*	`conf`	Understanding the Limitations of Conditional Generative Models. ICLR Ethan Fetaya, Jörn-Henrik Jacobsen, Will Grathwohl, Richard S. Zemel
2020	A*	`conf`	Your classifier is secretly an energy based model and you should treat it like one. ICLR Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Mohammad Norouzi, Kevin Swersky
2019	—	`conf`	FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models. ICLR Will Grathwohl, Ricky T. Q. Chen, Jesse Bettencourt, Ilya Sutskever, David Duvenaud
2019	A*	`conf`	Invertible Residual Networks. ICML Jens Behrmann, Will Grathwohl, Ricky T. Q. Chen, David Duvenaud, Jörn-Henrik Jacobsen
2019	J	`jnl`	Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One. CoRR Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Mohammad Norouzi, Kevin Swersky
2018	—	`conf`	Backpropagation through the Void: Optimizing control variates for black-box gradient estimation. ICLR (Poster) Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, David Duvenaud
2018	J	`jnl`	FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models. CoRR Will Grathwohl, Ricky T. Q. Chen, Jesse Bettencourt, Ilya Sutskever, David Duvenaud
2018	—	`conf`	Gradient-based Optimization of Neural Network Architecture. ICLR (Workshop) Will Grathwohl, Elliot Creager, Seyed Kamyar Seyed Ghasemipour, Richard S. Zemel
2017	J	`jnl`	Backpropagation through the Void: Optimizing control variates for black-box gradient estimation. CoRR Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, David Duvenaud
2016	J	`jnl`	Disentangling Space and Time in Video with Hierarchical Variational Auto-encoders. CoRR Will Grathwohl, Aaron Wilson