345 citations · 1.1k across the 20 of their papers we have counts for
20 papers
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Estimating Gibbs free energies via isobaric-isothermal flows
Peter Wirnsberger, Borja Ibarz, George Papamakarios
We present a machine-learning model based on normalizing flows that is trained to sample from the isobaric-isothermal ensemble. In our approach, we approximate the joint distributi…
Equivariant MuZero
Andreea Deac, Théophane Weber, George Papamakarios
Deep reinforcement learning repeatedly succeeds in closed, well-defined domains such as games (Chess, Go, StarCraft). The next frontier is real-world scenarios, where setups are nu…
Compositional Score Modeling for Simulation-based Inference
Tomas Geffner, George Papamakarios, Andriy Mnih
Neural Posterior Estimation methods for simulation-based inference can be ill-suited for dealing with posterior distributions obtained by conditioning on multiple observations, as…
A Generalist Neural Algorithmic Learner
Borja Ibarz, Vitaly Kurin, George Papamakarios +12
The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution. While recent years have seen a…
Normalizing flows for atomic solids
Peter Wirnsberger, George Papamakarios, Borja Ibarz +4
We present a machine-learning approach, based on normalizing flows, for modelling atomic solids. Our model transforms an analytically tractable base distribution into the target so…
The Lipschitz Constant of Self-Attention
Hyunjik Kim, George Papamakarios, Andriy Mnih
Lipschitz constants of neural networks have been explored in various contexts in deep learning, such as provable adversarial robustness, estimating Wasserstein distance, stabilisin…
Causally Correct Partial Models for Reinforcement Learning
Danilo J. Rezende, Ivo Danihelka, George Papamakarios +11
In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions. However, jointly modeling future observations can b…
Targeted free energy estimation via learned mappings
Peter Wirnsberger, Andrew J. Ballard, George Papamakarios +5
Free energy perturbation (FEP) was proposed by Zwanzig more than six decades ago as a method to estimate free energy differences, and has since inspired a huge body of related meth…
On Contrastive Learning for Likelihood-free Inference
Conor Durkan, Iain Murray, George Papamakarios
Likelihood-free methods perform parameter inference in stochastic simulator models where evaluating the likelihood is intractable but sampling synthetic data is possible. One class…
Normalizing Flows on Tori and Spheres
Danilo Jimenez Rezende, George Papamakarios, Sébastien Racanière +4
Normalizing flows are a powerful tool for building expressive distributions in high dimensions. So far, most of the literature has concentrated on learning flows on Euclidean space…
Normalizing Flows for Probabilistic Modeling and Inference
George Papamakarios, Eric Nalisnick, Danilo Jimenez Rezende +2
Normalizing flows provide a general mechanism for defining expressive probability distributions, only requiring the specification of a (usually simple) base distribution and a seri…
Neural Density Estimation and Likelihood-free Inference
George Papamakarios
I consider two problems in machine learning and statistics: the problem of estimating the joint probability density of a collection of random variables, known as density estimation…
Cubic-Spline Flows
Conor Durkan, Artur Bekasov, Iain Murray +1
A normalizing flow models a complex probability density as an invertible transformation of a simple density. The invertibility means that we can evaluate densities and generate sam…
Neural Spline Flows
Conor Durkan, Artur Bekasov, Iain Murray +1
A normalizing flow models a complex probability density as an invertible transformation of a simple base density. Flows based on either coupling or autoregressive transforms both o…
Sequential Neural Methods for Likelihood-free Inference
Conor Durkan, George Papamakarios, Iain Murray
Likelihood-free inference refers to inference when a likelihood function cannot be explicitly evaluated, which is often the case for models based on simulators. Most of the literat…
Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flows
George Papamakarios, David C. Sterratt, Iain Murray
We present Sequential Neural Likelihood (SNL), a new method for Bayesian inference in simulator models, where the likelihood is intractable but simulating data from the model is po…
Masked Autoregressive Flow for Density Estimation
George Papamakarios, Theo Pavlakou, Iain Murray
Autoregressive models are among the best performing neural density estimators. We describe an approach for increasing the flexibility of an autoregressive model, based on modelling…
Fast -free Inference of Simulation Models with Bayesian Conditional Density Estimation
George Papamakarios, Iain Murray
Many statistical models can be simulated forwards but have intractable likelihoods. Approximate Bayesian Computation (ABC) methods are used to infer properties of these models from…
Distilling Model Knowledge
George Papamakarios
Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and h…