Will Sussman Grathwohl
4 papers · 2021–2024 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
Top co-authors
Research topics
Keywords
energy-based model
(2)
diffusion model
(2)
generative model
(2)
monte carlo sampling
(1)
stochastic process
(1)
score matching
(1)
variational approximation
(1)
entropy regularization
(1)
compositional generation
(1)
amortized sampling
(1)
softmax approximation
(1)
normalizing constant
(1)
hard negative
(1)
cached embeddings
(1)
corrector network
(1)
dense retrieval
(1)
re-embedding computational cost
(1)
markov chain monte carlo
(1)
mcmc sampling
(1)
Papers
A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks
ICML 2024
Denoising Diffusion Samplers
ICLR 2023
Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
ICML 2023
No MCMC for me: Amortized sampling for fast and stable training of energy-based models
ICLR 2021