Will Grathwohl
10 papers · 2018–2023 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (3) 🏃 Academic Marathon (5) 🐝 Cross-Pollinator (13)
🌉
Interdisciplinary Bridge
🐣
Hot Topic Early Bird
🐝
Cross-Pollinator
(13)
🔥
Unstoppable
(6)
💎
Century Club
(10)
🚀
Conference Pioneer
Conferences
ICLR (4)
ICML (3)
NIPS (3)
Top co-authors
Keywords
markov chain monte carlo
(2)
gradient-based sampling
(2)
variational auto-encoder
(2)
energy-based model
(2)
metropolis-hastings sampling
(1)
fact verification
(1)
marginal likelihood
(1)
maximum likelihood
(1)
random walk
(1)
approximate sampling
(1)
discrete sampling
(1)
discrete distribution
(1)
annealed importance sampling
(1)
generative model
(1)
probabilistic model
(1)
graphical model
(1)
normalizing flow
(1)
unnormalized model
(1)
behavioral cloning
(1)
score-based diffusion
(1)
Papers
DISCS: A Benchmark for Discrete Sampling
NIPS 2023
Learning to Navigate Wikipedia by Taking Random Walks
NIPS 2022
Score-Based Diffusion meets Annealed Importance Sampling
NIPS 2022
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
ICML 2021
Understanding the Limitations of Conditional Generative Models
ICLR 2020
Your classifier is secretly an energy based model and you should treat it like one
ICLR 2020
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
ICML 2020
FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models
ICLR 2019
Invertible Residual Networks
ICML 2019
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
ICLR 2018