4 citations · 13 across the 20 of their papers we have counts for
27 papers
Characterizing and Mitigating Distributional Bias in Physics-Informed Generative Models
Tanja Bien, Samir Darouich, Lluís Pastor-Pérez +3
Physics-informed generative models augment a data-fitting objective with residual penalties that encourage physical constraints to hold in generated samples. However, improving con…
Geometry Meets Physics: Data-Efficient Pre-Training for Unstructured Neural PDE Solvers
Luis Medrano-Navarro, Giacomo Baldan, Qiang Liu +4
Neural surrogate models for Partial Differential Equations (PDEs) on unstructured 3D geometries are often limited by poor generalization and the high cost of generating large-scale…
Learned End-to-End Guidance Schedules for Diffusion Models
Aneesh Barthakur, Mathias Niepert, Luiz F. O. Chamon
Diffusion models are a powerful generative paradigm used across multimedia and scientific applications. Guided diffusion methods impose requirements on the generation by adding the…
Fine-Tuning Diffusion Language Models with Context Selection and Target Weighting
Loay Mualem, Lluís Pastor-Pérez, Vinh Tong +4
Supervised fine-tuning of discrete diffusion language models masks some response tokens and trains the model to recover their original values from the visible context. The masking…
Parallel Tempering for Diffusion-Based Combinatorial Optimization
Arman Mielke, Uwe Bauknecht, Thilo Strauss +1
Discrete diffusion models have emerged as a powerful paradigm for solving combinatorial optimization (CO) problems on graphs by learning to sample high-quality solutions. A common…
Equivariance Breaks the Learning Rate
Andrei Manolache, Mathias Niepert
Equivariant networks are commonly trained with Adam, yet recent work reports that matrix structured optimizers such as Muon can perform better, with the reasons for these gains onl…
Distillation of Foundation Models for Time-dependent PDEs
Daniel Musekamp, Boshra Ariguib, Andrei Manolache +1
Foundation models for time-dependent partial differential equations (PDEs) are trained on large and diverse collections of physical systems and can generalize effectively to new do…
ARIA: Adaptive Region-Based Importance Allocation for Conditional Diffusion Distillation
Loay Mualem, Vinh Tong, Samir Darouich +1
Distilling conditional diffusion models aims to transfer the behavior of a large teacher to a smaller student while preserving alignment across conditioning inputs. Unlike recognit…
SymDrift: One-Shot Generative Modeling under Symmetries
Samir Darouich, Vinh Tong, Lluís Pastor-Pérez +3
Generative modeling of physical systems, such as molecules, requires learning distributions that are invariant under global symmetries, such as rotations in three-dimensional space…
GraIP: A Benchmarking Framework For Neural Graph Inverse Problems
Semih Cantürk, Andrei Manolache, Arman Mielke +5
A wide range of graph learning tasks, such as structure discovery, temporal graph analysis, and combinatorial optimization, focus on inferring graph structures from data, rather th…
SMART: Scalable Mesh-free Aerodynamic Simulations from Raw Geometries using a Transformer-based Surrogate Model
Jan Hagnberger, Mathias Niepert
Machine learning-based surrogate models have emerged as more efficient alternatives to numerical solvers for physical simulations over complex geometries, such as car bodies. Many…
GraphBench: Next-generation graph learning benchmarking
Timo Stoll, Chendi Qian, Ben Finkelshtein +16
Machine learning on graphs has made substantial progress across domains such as molecular property prediction and chip design. Yet benchmarking practices remain fragmented, often r…
Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
Boshra Ariguib, Mathias Niepert, Andrei Manolache
High-quality molecular representations are essential for property prediction and molecular design, yet large labeled datasets remain scarce. While self-supervised pretraining on mo…
Learning (Approximately) Equivariant Networks via Constrained Optimization
Andrei Manolache, Luiz F. O. Chamon, Mathias Niepert
Equivariant neural networks are designed to respect symmetries through their architecture, boosting generalization and sample efficiency when those symmetries are present in the da…
CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs
Jan Hagnberger, Daniel Musekamp, Mathias Niepert
Solving time-dependent Partial Differential Equations (PDEs) using a densely discretized spatial domain is a fundamental problem in various scientific and engineering disciplines,…
LOGLO-FNO: Efficient Learning of Local and Global Features in Fourier Neural Operators
Marimuthu Kalimuthu, David Holzmüller, Mathias Niepert
Modeling high-frequency information is a critical challenge in scientific machine learning. For instance, fully turbulent flow simulations of the Navier-Stokes equations at Reynold…
Preference-Based Gradient Estimation for ML-Guided Approximate Combinatorial Optimization
Arman Mielke, Uwe Bauknecht, Thilo Strauss +1
Combinatorial optimization (CO) problems arise across a broad spectrum of domains, including medicine, logistics, and manufacturing. While exact solutions are often computationally…
Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion
Vinh Tong, Hoang Trung-Dung, Anji Liu +2
In domains such as molecular and protein generation, physical systems exhibit inherent symmetries that are critical to model. Two main strategies have emerged for learning invarian…
Tractable Transformers for Flexible Conditional Generation
Anji Liu, Xuejie Liu, Dayuan Zhao +3
Non-autoregressive (NAR) generative models are valuable because they can handle diverse conditional generation tasks in a more principled way than their autoregressive (AR) counter…
MolMix: A Simple Yet Effective Baseline for Multimodal Molecular Representation Learning
Andrei Manolache, Dragos Tantaru, Mathias Niepert
In this work, we propose a simple transformer-based baseline for multimodal molecular representation learning, integrating three distinct modalities: SMILES strings, 2D graph repre…
Discrete Copula Diffusion
Anji Liu, Oliver Broadrick, Mathias Niepert +1
Discrete diffusion models have recently shown significant progress in modeling complex data, such as natural languages and DNA sequences. However, unlike diffusion models for conti…
Active Learning for Neural PDE Solvers
Daniel Musekamp, Marimuthu Kalimuthu, David Holzmüller +2
Solving partial differential equations (PDEs) is a fundamental problem in science and engineering. While neural PDE solvers can be more efficient than established numerical solvers…
Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations
Jan Hagnberger, Marimuthu Kalimuthu, Daniel Musekamp +1
Transformer models are increasingly used for solving Partial Differential Equations (PDEs). Several adaptations have been proposed, all of which suffer from the typical problems of…
Probabilistic Graph Rewiring via Virtual Nodes
Chendi Qian, Andrei Manolache, Christopher Morris +1
Message-passing graph neural networks (MPNNs) have emerged as a powerful paradigm for graph-based machine learning. Despite their effectiveness, MPNNs face challenges such as under…