David Duvenaud

Computer Science · Physical Sciences

43h-index10.8kcitations113works6.22yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

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

Research Topics

Gaussian Processes and Bayesian Inference(32), Generative Adversarial Networks and Image Synthesis(28), Model Reduction and Neural Networks(20), Adversarial Robustness in Machine Learning(16), Neural Networks and Applications(15)

Publications113 total

Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value
arXiv (Cornell University)·2025Open Access
JoLT: Joint Probabilistic Predictions on Tabular Data Using LLMs
arXiv (Cornell University)·2025Open Access
Alignment faking in large language models
arXiv (Cornell University)·2024· 17 citedOpen Access
Sabotage Evaluations for Frontier Models
arXiv (Cornell University)·2024· 2 citedOpen Access
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
arXiv (Cornell University)·2024· 4 citedOpen Access
LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language
arXiv (Cornell University)·2024· 6 citedOpen Access
Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs
arXiv (Cornell University)·2024· 1 citedOpen Access
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
arXiv (Cornell University)·2024· 29 citedOpen Access
Many-shot Jailbreaking
2024· 2 cited
LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language
2024· 1 cited
Sorting Out Quantum Monte Carlo
arXiv (Cornell University)·2023· 1 citedOpen Access
Tools for Verifying Neural Models' Training Data
arXiv (Cornell University)·2023· 1 citedOpen Access
On Implicit Bias in Overparameterized Bilevel Optimization
arXiv (Cornell University)·2022· 3 citedOpen Access
Meta-Learning to Improve Pre-Training
arXiv (Cornell University)·2021Open Access
Getting to the point: index sets and parallelism-preserving autodiff for pointful array programming
Proceedings of the ACM on Programming Languages·2021· 1 citedOpen Access
Getting to the Point. Index Sets and Parallelism-Preserving Autodiff for\n Pointful Array Programming
arXiv (Cornell University)·2021· 1 citedOpen Access
Complex Momentum for Learning in Games.
arXiv (Cornell University)·2021Open Access
Complex Momentum for Optimization in Games
arXiv (Cornell University)·2021Open Access
Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations
arXiv (Cornell University)·2021· 15 citedOpen Access
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
arXiv (Cornell University)·2021· 8 citedOpen Access
page 1 of 6Next →

Frequent Co-authors

Ricky T. Q. Chen(12), Roger Grosse(10), Ryan P. Adams(8), Will Grathwohl(6), Zoubin Ghahramani(6), Joshua B. Tenenbaum(5), Dougal Maclaurin(4), Jesse Bettencourt(4), James Robert Lloyd(4), Jens Behrmann(4), Rafael Gómez‐Bombarelli(3), Jorge Aguilera‐Iparraguirre(3), Timothy Hirzel(3), Alán Aspuru‐Guzik(3), Yulia Rubanova(3), Matthew Johnson(3), Jörn-Henrik Jacobsen(3), Xuechen Li(3), Jonathan Lorraine(3), Paul Vicol(3)