131 citations · 179 across the 26 of their papers we have counts for
31 papers
On the Selectivity of Generative Models in Structure-Based Drug Design
Ella Miray Rajaonson, Jungyoon Lee, William Chau +5
Designing small-molecule drugs that selectively bind to a target protein while avoiding unintended interactions with other proteins is essential for reducing side effects that cont…
Scaling Density Functional Theory with Gaussian Splatting
Andrés Guzmán-Cordero, Cindy Zhang, Majdi Hassan +3
Density functional theory (DFT) strikes a practical balance between accuracy and computational cost in many problems of computational chemistry and materials science. However, many…
A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
Vincent Guan, Lazar Atanackovic, Kirill Neklyudov
The population dynamics of molecules, cells, and organisms are governed by a number of unknown forces. In the last decade, population dynamics have predominantly been modeled with…
General Multimodal Protein Design Enables DNA-Encoding of Chemistry
Jarrid Rector-Brooks, Théophile Lambert, Marta Skreta +15
Evolution is an extraordinary engine for enzymatic diversity, yet the chemistry it has explored remains a narrow slice of what DNA can encode. Deep generative models can design new…
Discrete Feynman-Kac Correctors
Mohsin Hasan, Viktor Ohanesian, Artem Gazizov +5
Discrete diffusion models have recently emerged as a promising alternative to the autoregressive approach for generating discrete sequences. Sample generation via gradual denoising…
Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction
Vincent Pauline, Tobias Höppe, Kirill Neklyudov +3
Although diffusion models now occupy a central place in generative modeling, introductory treatments commonly assume Euclidean data and seldom clarify their connection to discrete-…
Wavefunction Flows: Efficient Quantum Simulation of Continuous Flow Models
David Layden, Ryan Sweke, Vojtěch Havlíček +2
Flow models are a cornerstone of modern machine learning. They are generative models that progressively transform probability distributions according to learned dynamics. Specifica…
Amortized Sampling with Transferable Normalizing Flows
Charlie B. Tan, Majdi Hassan, Leon Klein +5
Efficient equilibrium sampling of molecular conformations remains a core challenge in computational chemistry and statistical inference. Classical approaches such as molecular dyna…
Self-Refining Training for Amortized Density Functional Theory
Majdi Hassan, Cristian Gabellini, Hatem Helal +2
Density Functional Theory (DFT) allows for predicting all the chemical and physical properties of molecular systems from first principles by finding an approximate solution to the…
Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
Tara Akhound-Sadegh, Jungyoon Lee, Avishek Joey Bose +7
Sampling efficiently from a target unnormalized probability density remains a core challenge, with relevance across countless high-impact scientific applications. A promising appro…
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
Marta Skreta, Tara Akhound-Sadegh, Viktor Ohanesian +6
While score-based generative models are the model of choice across diverse domains, there are limited tools available for controlling inference-time behavior in a principled manner…
The Superposition of Diffusion Models Using the Itô Density Estimator
Marta Skreta, Lazar Atanackovic, Avishek Joey Bose +2
The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurrin…
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
Yuanqi Du, Michael Plainer, Rob Brekelmans +5
Rare event sampling in dynamical systems is a fundamental problem arising in the natural sciences, which poses significant computational challenges due to an exponentially large sp…
Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold
Lazar Atanackovic, Xi Zhang, Brandon Amos +5
Numerous biological and physical processes can be modeled as systems of interacting entities evolving continuously over time, e.g. the dynamics of communicating cells or physical p…
Efficient Evolutionary Search Over Chemical Space with Large Language Models
Haorui Wang, Marta Skreta, Cher-Tian Ser +11
Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectives can be non-differentiable. Evolutiona…
Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints
Lingkai Kong, Yuanqi Du, Wenhao Mu +8
Addressing real-world optimization problems becomes particularly challenging when analytic objective functions or constraints are unavailable. While numerous studies have addressed…
Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC
Wu Lin, Felix Dangel, Runa Eschenhagen +4
Second-order methods such as KFAC can be useful for neural net training. However, they are often memory-inefficient since their preconditioning Kronecker factors are dense, and num…
A Computational Framework for Solving Wasserstein Lagrangian Flows
Kirill Neklyudov, Rob Brekelmans, Alexander Tong +3
The dynamical formulation of the optimal transport can be extended through various choices of the underlying geometry (kinetic energy), and the regularization of density paths (pot…
Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schrödinger Equation
Kirill Neklyudov, Jannes Nys, Luca Thiede +4
Solving the quantum many-body Schrödinger equation is a fundamental and challenging problem in the fields of quantum physics, quantum chemistry, and material sciences. One of the c…
Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition
Juan Carrasquilla, Mohamed Hibat-Allah, Estelle Inack +4
Binary neural networks, i.e., neural networks whose parameters and activations are constrained to only two possible values, offer a compelling avenue for the deployment of deep lea…
Action Matching: Learning Stochastic Dynamics from Samples
Kirill Neklyudov, Rob Brekelmans, Daniel Severo +1
Learning the continuous dynamics of a system from snapshots of its temporal marginals is a problem which appears throughout natural sciences and machine learning, including in quan…
Particle Dynamics for Learning EBMs
Kirill Neklyudov, Priyank Jaini, Max Welling
Energy-based modeling is a promising approach to unsupervised learning, which yields many downstream applications from a single model. The main difficulty in learning energy-based…
Deterministic Gibbs Sampling via Ordinary Differential Equations
Kirill Neklyudov, Roberto Bondesan, Max Welling
Deterministic dynamics is an essential part of many MCMC algorithms, e.g. Hybrid Monte Carlo or samplers utilizing normalizing flows. This paper presents a general construction of…
Orbital MCMC
Kirill Neklyudov, Max Welling
Markov Chain Monte Carlo (MCMC) algorithms ubiquitously employ complex deterministic transformations to generate proposal points that are then filtered by the Metropolis-Hastings-G…