John Thickstun
8 papers · 2020–2023 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (6) π Cross-Pollinator (15) π Renaissance Researcher (7)
πΊοΈ
Taxonomy Completionist
(24)
π£
Hot Topic Early Bird
Conferences
ICML (2)
NIPS (2)
ACL (1)
EMNLP (1)
JMLR (1)
L4DC (1)
Top co-authors
Research topics
Keywords
text generation
(3)
generative model
(3)
controllable generation
(2)
langevin dynamics
(2)
source separation
(2)
language modeling
(2)
language model
(2)
information bottleneck
(1)
bayesian inference
(1)
semi-supervised learning
(1)
feature selection
(1)
rationale extraction
(1)
policy learning
(1)
speech enhancement
(1)
image restoration
(1)
distribution matching
(1)
posterior distribution
(1)
model interpretability
(1)
adaptive discretization
(1)
neural architecture
(1)
Papers
MAUVE Scores for Generative Models: Theory and Practice
JMLR 2023
Backpack Language Models
ACL 2023
Diffusion-LM Improves Controllable Text Generation
NIPS 2022
MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers
NIPS 2021
Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics
ICML 2021
Faster Policy Learning with Continuous-Time Gradients
L4DC 2021
Source Separation with Deep Generative Priors
ICML 2020
An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction
EMNLP 2020