publications
Everything, newest first. Use the filter to search titles, authors and venues.
2026
- Simplex Diffusion Models
- DiffusionGemma Technical Report
- Diffusion Fine-tuning with Rewarded Moment Matching Distillation
- Adversarial Learning of Classifier-Free Guidance Schedules
- Accelerating Speculative Diffusions via Block Verification
- On the Wasserstein Gradient Flow Interpretation of Drifting Models
- AsyncPatch Diffusion: Spatially-Flexible Image Generation
- Seasoning Generative Models for a Generalization Aftertaste
- Count Bridges enable Modeling and Deconvolving Transcriptomic Data
2025
- Dimension-Free Error Estimate for Diffusion Model and Optimal Scheduling
- Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
- On the Edge of Memorization in Diffusion Models
Studies where diffusion models stop generalising and start reproducing their training data, and what controls the boundary between the two.
- Distributional Diffusion Models with Scoring Rules
- From Stability of Langevin Diffusion to Convergence of Proximal MCMC for Non-Log-Concave Sampling
- Self-Speculative Masked Diffusions
- Learn to Guide Your Diffusion Model
- Accelerated Diffusion Models via Speculative Sampling
- Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints
2024
- Particle Denoising Diffusion Sampler
- Schrödinger Bridge Flow for Unpaired Data Translation
- Implicit Diffusion: Efficient Optimization through Stochastic Sampling
- Deep MMD Gradient Flow without Adversarial Training
- Solving a Class of Fredholm Integral Equations of the First Kind via Wasserstein Gradient Flows
- Target Score Matching
2023
- Diffusion Schrödinger Bridge Matching
Reformulates the Schrodinger bridge as iterative Markovian fitting, removing the error that accumulated across outer iterations in earlier bridge solvers.
- SE(3) Diffusion Model with Application to Protein Backbone Generation
A diffusion model on SE(3) that generates protein backbones by denoising the rigid-body frame of each residue.
- Trans-Dimensional Generative Modeling via Jump Diffusion Models
- Nearly d-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
- Particle Guidance: Non-I.I.D. Diverse Sampling with Diffusion Models
- Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters
- Metropolis Sampling for Constrained Diffusion Models
- Geometric Neural Diffusion Processes
- Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
- Diffusion Models for Constrained Domains
- Augmented Bridge Matching
- Diffusion Schrödinger Bridges for Bayesian Computation
2022
- Convergence of Denoising Diffusion Models under the Manifold Hypothesis
Convergence guarantees for denoising diffusions when the data lies on a low-dimensional manifold - the regime where the score is unbounded and earlier analyses break down.
- From Denoising Diffusions to Denoising Markov Models
- Riemannian Score-Based Generative Modelling
Extends score-based generative models from Euclidean space to Riemannian manifolds, so data living on spheres, tori and other geometries is modelled in its own coordinates.
- A Continuous Time Framework for Discrete Denoising Models
- Wavelet Score-Based Generative Modeling
- Can Push-Forward Generative Models Fit Multimodal Distributions?
- Unbiased Constrained Sampling with Self-Concordant Barrier Hamiltonian Monte Carlo
- Conditional Simulation Using Diffusion Schrödinger Bridges
- Riemannian Diffusion Schrödinger Bridge
- Spectral Diffusion Processes
- On Maximum a Posteriori Estimation with Plug & Play Priors and Stochastic Gradient Descent
- An Introduction to Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks
2021
- Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
Casts generative modelling as a Schrodinger bridge - an entropic optimal transport problem - and solves it by iterative proportional fitting on learned scores.
- On Quantitative Laplace-Type Convergence Results for Some Exponential Probability Measures, with Two Applications
- Simulating Diffusion Bridges with Score Matching
- Quantitative Uniform Stability of the Iterative Proportional Fitting Procedure
- Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
- Maximum Entropy Methods for Texture Synthesis: Theory and Practice
- Continuous and Discrete-Time Analysis of Stochastic Gradient Descent for Convex and Non-Convex Functions
2020
- Quantitative Propagation of Chaos for SGD in Wide Neural Networks
- Approximate Bayesian Computation with the Sliced-Wasserstein Distance
- Maximum Likelihood Estimation of Regularisation Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach. Part I: Methodology and Experiments
- Maximum Likelihood Estimation of Regularisation Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach. Part II: Theoretical Analysis
- Redundancy in Gaussian Random Fields
- Efficient Stochastic Optimisation by Unadjusted Langevin Monte Carlo. Application to Maximum Marginal Likelihood and Empirical Bayesian Estimation
- Non-Local Statistics in Images: Modelling, Estimation and Sampling
2019
- Patch Redundancy in Images: A Statistical Testing Framework and Some Applications
- Macrocanonical Models for Texture Synthesis
- Convergence of Diffusions and Their Discretizations: From Continuous to Discrete Processes and Back
2018
- Review of Wavelet-Based Unsupervised Texture Segmentation, Advantage of Adaptive Wavelets