Free-form flows: Make any architecture a normalizing flow
Normalizing Flows are generative models that directly maximize the likelihood. Previously,
the design of normalizing flows was largely constrained by the need for analytical …
the design of normalizing flows was largely constrained by the need for analytical …
Steering masked discrete diffusion models via discrete denoising posterior prediction
Generative modeling of discrete data underlies important applications spanning text-based
agents like ChatGPT to the design of the very building blocks of life in protein sequences …
agents like ChatGPT to the design of the very building blocks of life in protein sequences …
All-in-one simulation-based inference
Amortized Bayesian inference trains neural networks to solve stochastic inference problems
using model simulations, thereby making it possible to rapidly perform Bayesian inference …
using model simulations, thereby making it possible to rapidly perform Bayesian inference …
Compositional simulation-based inference for time series
Amortized simulation-based inference (SBI) methods train neural networks on simulated
data to perform Bayesian inference. While this approach avoids the need for tractable …
data to perform Bayesian inference. While this approach avoids the need for tractable …
Variational Flow Matching for Graph Generation
We present a formulation of flow matching as variational inference, which we refer to as
variational flow matching (VFM). Based on this formulation we develop CatFlow, a flow …
variational flow matching (VFM). Based on this formulation we develop CatFlow, a flow …
A kernel-based conditional two-sample test using nearest neighbors (with applications to calibration, regression curves, and simulation-based inference)
In this paper we introduce a kernel-based measure for detecting differences between two
conditional distributions. Using thekernel trick'and nearest-neighbor graphs, we propose a …
conditional distributions. Using thekernel trick'and nearest-neighbor graphs, we propose a …
Synthesizing 3D Abstractions by Inverting Procedural Buildings with Transformers
M Dax, J Berbel, J Stria, L Guibas… - arxiv preprint arxiv …, 2025 - arxiv.org
We generate abstractions of buildings, reflecting the essential aspects of their geometry and
structure, by learning to invert procedural models. We first build a dataset of abstract …
structure, by learning to invert procedural models. We first build a dataset of abstract …
SGFM: Conditional Flow Matching for Time Series Anomaly Detection With State Space Models
Y He, T Yan, Y Zhan, Z Feng… - IEEE Internet of Things …, 2024 - ieeexplore.ieee.org
The industrial Internet of Things (IoT) landscape is enriched with a diverse array of sensors,
which are configured for the real-time monitoring and data collection to improve the …
which are configured for the real-time monitoring and data collection to improve the …
Amortized Bayesian Multilevel Models
D Habermann, M Schmitt, L Kühmichel… - arxiv preprint arxiv …, 2024 - arxiv.org
Multilevel models (MLMs) are a central building block of the Bayesian workflow. They
enable joint, interpretable modeling of data across hierarchical levels and provide a fully …
enable joint, interpretable modeling of data across hierarchical levels and provide a fully …
The Unreasonable Effectiveness of Solving Inverse Problems with Neural Networks
Finding model parameters from data is an essential task in science and engineering, from
weather and climate forecasts to plasma control. Previous works have employed neural …
weather and climate forecasts to plasma control. Previous works have employed neural …