Publications (18)
OpenAI o1 System Card
OpenAI, :, Aaron Jaech +261
The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the…
Modeling nonlinear scales for dynamical dark energy cosmologies with COLA
João Rebouças, Victoria Lloyd, Jonathan Gordon +2
Upcoming galaxy surveys will bring a wealth of information about the clustering of matter, but modeling small-scale structure beyond CDM remains computationally challenging. Wh…
Bayesian Batch Active Learning as Sparse Subset Approximation
Robert Pinsler, Jonathan Gordon, Eric Nalisnick +1
Leveraging the wealth of unlabeled data produced in recent years provides great potential for improving supervised models. When the cost of acquiring labels is high, probabilistic…
Probabilistic Neural Architecture Search
Francesco Paolo Casale, Jonathan Gordon, Nicolo Fusi
In neural architecture search (NAS), the space of neural network architectures is automatically explored to maximize predictive accuracy for a given task. Despite the success of re…
Early dark energy constraints with late-time expansion marginalization
João Rebouças, Jonathan Gordon, Diogo H. F. de Souza +5
Early dark energy (EDE) is an extension to the CDM model, proposed to reduce the tension between the measurements of the Hubble constant from the cosmic microwave backgro…
Meta-Learning Probabilistic Inference For Prediction
Jonathan Gordon, John Bronskill, Matthias Bauer +2
This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic…
Predictive Complexity Priors
Eric Nalisnick, Jonathan Gordon, José Miguel Hernández-Lobato
Specifying a Bayesian prior is notoriously difficult for complex models such as neural networks. Reasoning about parameters is made challenging by the high-dimensionality and over-…
Bayesian Semisupervised Learning with Deep Generative Models
Jonathan Gordon, José Miguel Hernández-Lobato
Neural network based generative models with discriminative components are a powerful approach for semi-supervised learning. However, these techniques a) cannot account for model un…
GPT-4 Technical Report
OpenAI, Josh Achiam, Steven Adler +278
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-wor…
An Investigation into the Pedagogical Features of Documents
Emily Sheng, Prem Natarajan, Jonathan Gordon +1
Characterizing the content of a technical document in terms of its learning utility can be useful for applications related to education, such as generating reading lists from large…
Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
Andrew Y. K. Foong, Wessel P. Bruinsma, Jonathan Gordon +3
Stationary stochastic processes (SPs) are a key component of many probabilistic models, such as those for off-the-grid spatio-temporal data. They enable the statistical symmetry of…
TaskNorm: Rethinking Batch Normalization for Meta-Learning
John Bronskill, Jonathan Gordon, James Requeima +2
Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential compone…
Evolution through Large Models
Joel Lehman, Jonathan Gordon, Shawn Jain +3
This paper pursues the insight that large language models (LLMs) trained to generate code can vastly improve the effectiveness of mutation operators applied to programs in genetic…
The Gaussian Neural Process
Wessel P. Bruinsma, James Requeima, Andrew Y. K. Foong +2
Neural Processes (NPs; Garnelo et al., 2018a,b) are a rich class of models for meta-learning that map data sets directly to predictive stochastic processes. We provide a rigorous a…
OpenAI GPT-5 System Card
Aaditya Singh, Adam Fry, Adam Perelman +483
This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reason…
Convolutional Conditional Neural Processes
Jonathan Gordon, Wessel P. Bruinsma, Andrew Y. K. Foong +3
We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data. Translation equivar…
Modeling nonlinear scales with COLA: preparing for LSST-Y1
Jonathan Gordon, Bernardo F. de Aguiar, João Rebouças +5
Year 1 results of the Legacy Survey of Space and Time (LSST) will provide tighter constraints on small-scale cosmology, beyond the validity of linear perturbation theory. This heig…
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
James Requeima, Jonathan Gordon, John Bronskill +2
The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We…