John Lafferty

Northwestern University — United States

Mathematics · Physical Sciences

75h-index47.7kcitations293works3.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Statistical Methods and Inference(48), Natural Language Processing Techniques(41), Topic Modeling(37), Bayesian Modeling and Causal Inference(29), Neural Networks and Applications(28)

Publications293 total

Pressure-Induced Three- to Two-Dimensional Structural Transition in Light Lanthanide Trichlorides
Inorganic Chemistry·2025
Confidence Intervals for Linear Models with Arbitrary Noise Contamination
arXiv (Cornell University)·2025Open Access
CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision
arXiv (Cornell University)·2025Open Access
Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
arXiv (Cornell University)·2024Open Access
Images with harder-to-reconstruct visual representations leave stronger memory traces
Nature Human Behaviour·2024· 13 cited
The relational bottleneck as an inductive bias for efficient abstraction
Trends in Cognitive Sciences·2024· 16 cited
ACM/IMS <i>Journal of Data Science</i> : Inaugural Issue Editorial
ACM / IMS Journal of Data Science·2024Open Access
Approximation of relation functions and attention mechanisms
arXiv (Cornell University)·2024· 2 citedOpen Access
Learning Hierarchical Relational Representations through Relational Convolutions
arXiv (Cornell University)·2023· 1 citedOpen Access
The Relational Bottleneck as an Inductive Bias for Efficient Abstraction
arXiv (Cornell University)·2023· 5 citedOpen Access
Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers
arXiv (Cornell University)·2023· 6 citedOpen Access
From seeing to remembering: Images with harder-to-reconstruct representations leave stronger memory traces
arXiv (Cornell University)·2023Open Access
Images that are harder to reconstruct are more memorable and benefit more from additional encoding times
Journal of Vision·2022Open Access
Emergent organization of receptive fields in networks of excitatory and inhibitory neurons
arXiv (Cornell University)·2022Open Access
Shallow neural networks trained to detect collisions recover features of visual loom-selective neurons
eLife·2022· 31 citedOpen Access
Author response: Shallow neural networks trained to detect collisions recover features of visual loom-selective neurons
2021Open Access
Shallow neural networks trained to detect collisions recover features of visual loom-selective neurons
2021Open Access
Convergence and Alignment of Gradient Descent with Random Backpropagation Weights
arXiv (Cornell University)·2021· 5 citedOpen Access
Convergence and Alignment of Gradient Descent with Random\n Backpropagation Weights
arXiv (Cornell University)·2021· 2 citedOpen Access
The huge Package for High-dimensional Undirected Graph Estimation in R
PubMed·2020· 485 citedOpen Access
page 1 of 15Next →

Frequent Co-authors

ChengXiang Zhai(10), Xiaojin Zhu(5), Larry Wasserman(5), David M. Blei(4), Adam Berger(4), Zoubin Ghahramani(3), Robert L. Mercer(3), Guy Lebanon(3), Andrew McCallum(2), Peter F. Brown(2), Stephen A. Della Pietra(2), Vincent J. Della Pietra(2), Roni Rosenfeld(2), William W. Cohen(2), Han Liu(2), Salim Roukos(2), Pradeep Ravikumar(2), Fernando C. N. Pereira(1), John Cocke(1), Fredrick Jelinek(1)