Thomas Griffiths
9 papers · 2007–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) πΊοΈ Taxonomy Completionist (13) π§ Keyword Pioneer π Conference Polyglot (6) π Academic Marathon (17)
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
π
Conference Pioneer
β
The Questioner
Conferences
EMNLP (2)
ICLR (2)
NAACL (2)
AAAI (1)
ACL (1)
CONLL (1)
Top co-authors
Keywords
information theory
(1)
transformer architecture
(1)
representation learning
(1)
state abstraction
(1)
hierarchical planning
(1)
masked language model
(1)
serial reproduction
(1)
cognitive control
(1)
prior distribution
(1)
sampling method
(1)
creative problem solving
(1)
neural language model
(1)
syntactic representation
(1)
syntactic generalization
(1)
probing method
(1)
generative stochastic network
(1)
physical reasoning
(1)
grammatical construction
(1)
large language model
(1)
verb bia
(1)
Papers
MacGyver: Are Large Language Models Creative Problem Solvers?
NAACL 2024
Probing BERTβs priors with serial reproduction chains
ACL 2022
Meta-Learning of Structured Task Distributions in Humans and Machines
ICLR 2021
Investigating representations of verb bias in neural language models
EMNLP 2020
People Do Not Just Plan,They Plan to Plan
AAAI 2020
Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
ICLR 2018
A Probabilistic Approach to Diachronic Phonology
EMNLP 2007
Bayesian Inference for PCFGs via Markov Chain Monte Carlo
NAACL 2007
A Probabilistic Approach to Diachronic Phonology
CONLL 2007