78 citations · 253 across the 56 of their papers we have counts for
29 papers · 1 filter
Latent Diffusion for Missing Data
Alberte Heering Estad, Ignacio Peis, Jes Frellsen
Diffusion models have emerged as powerful generative approaches for missing-data imputation, yet most existing methods operate directly in data space and degrade when training data…
Towards More General Control of Diffusion Models Using Jeffrey Guidance
Raphaël Razafindralambo, Rémy Sun, Frédéric Precioso +2
A key strength of diffusion models lies in their flexibility, since their outputs can be controlled at sampling time through guidance. However, beyond simple cases such as conditio…
Order-Agnostic Autoregressive Modelling with Missing Data
Ignacio Peis, Pablo M. Olmos, Jes Frellsen
Order-Agnostic autoregressive models have demonstrated strong performance in deep generative modeling, yet their use in settings with incomplete data remains largely unexplored. In…
Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings
Paul Jeha, Anastasiia Sedova, Louis Béthune +4
For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization…
Tracing Uncertainty in Language Model "Reasoning"
Nils Grünefeld, Bertram Højer, Philipp Mondorf +5
Language model (LM) "reasoning", commonly described as Chain-of-Thought or test-time scaling, often improves benchmark performance, but the dynamics underlying this process remain…
Noise-Response Calibration: A Causal Intervention Protocol for LLM-Judges
Maxim Khomiakov, Jes Frellsen
Large language models (LLMs) are increasingly used as automated judges and synthetic labelers, especially in low-label settings. Yet these systems are stochastic and often overconf…
An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms
Nils Grünefeld, Jes Frellsen, Christian Hardmeier
Existing methods for quantifying predictive uncertainty in neural networks are either computationally intractable for large language models or require access to training data that…
Supervised Guidance Training for Infinite-Dimensional Diffusion Models
Elizabeth L. Baker, Alexander Denker, Jes Frellsen
Score-based diffusion models have recently been extended to infinite-dimensional function spaces, with uses such as inverse problems arising from partial differential equations. In…
Kinetic Langevin Diffusion for Crystalline Materials Generation
François Cornet, Federico Bergamin, Arghya Bhowmik +3
Generative modeling of crystalline materials using diffusion models presents a series of challenges: the data distribution is characterized by inherent symmetries and involves mult…
Exploring bidirectional bounds for minimax-training of Energy-based models
Cong Geng, Jia Wang, Li Chen +3
Energy-based models (EBMs) estimate unnormalized densities in an elegant framework, but they are generally difficult to train. Recent work has linked EBMs to generative adversarial…
Zero-shot protein stability prediction by inverse folding models: a free energy interpretation
Jes Frellsen, Maher M. Kassem, Tone Bengtsen +4
Inverse folding models have proven to be highly effective zero-shot predictors of protein stability. Despite this success, the link between the amino acid preferences of an inverse…
Hyper-Transforming Latent Diffusion Models
Ignacio Peis, Batuhan Koyuncu, Isabel Valera +1
We introduce a novel generative framework for functions by integrating Implicit Neural Representations (INRs) and Transformer-based hypernetworks into latent variable models. Unlik…
Learning Energy-Based Models by Self-normalising the Likelihood
Hugo Senetaire, Paul Jeha, Pierre-Alexandre Mattei +1
Training an energy-based model (EBM) with maximum likelihood is challenging due to the intractable normalisation constant. Traditional methods rely on expensive Markov chain Monte…
Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo
Cheuk Kit Lee, Paul Jeha, Jes Frellsen +3
Discrete diffusion models are a class of generative models that produce samples from an approximated data distribution within a discrete state space. Often, there is a need to targ…
MolMiner: Toward Controllable, 3D-Aware, Fragment-Based Molecular Design
Raul Ortega-Ochoa, Tejs Vegge, Jes Frellsen
We introduce MolMiner, a fragment-based, geometry-aware, and order-agnostic autoregressive model for molecular design. MolMiner supports high-dimensional conditional control over t…
Variance reduction of diffusion model's gradients with Taylor approximation-based control variate
Paul Jeha, Will Grathwohl, Michael Riis Andersen +2
Score-based models, trained with denoising score matching, are remarkably effective in generating high dimensional data. However, the high variance of their training objective hind…
Scalable physical source-to-field inference with hypernetworks
Berian James, Stefan Pollok, Ignacio Peis +3
We present a generative model that amortises computation for the field and potential around e.g.~gravitational or electromagnetic sources. Exact numerical calculation has either co…
A Continuous Relaxation for Discrete Bayesian Optimization
Richard Michael, Simon Bartels, Miguel González-Duque +4
To optimize efficiently over discrete data and with only few available target observations is a challenge in Bayesian optimization. We propose a continuous relaxation of the object…
Implicit Variational Inference for High-Dimensional Posteriors
Anshuk Uppal, Kristoffer Stensbo-Smidt, Wouter Boomsma +1
In variational inference, the benefits of Bayesian models rely on accurately capturing the true posterior distribution. We propose using neural samplers that specify implicit distr…
Internal-Coordinate Density Modelling of Protein Structure: Covariance Matters
Marloes Arts, Jes Frellsen, Wouter Boomsma
After the recent ground-breaking advances in protein structure prediction, one of the remaining challenges in protein machine learning is to reliably predict distributions of struc…
Explainability as statistical inference
Hugo Henri Joseph Senetaire, Damien Garreau, Jes Frellsen +1
A wide variety of model explanation approaches have been proposed in recent years, all guided by very different rationales and heuristics. In this paper, we take a new route and ca…
deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
Dennis Ulmer, Christian Hardmeier, Jes Frellsen
A lot of Machine Learning (ML) and Deep Learning (DL) research is of an empirical nature. Nevertheless, statistical significance testing (SST) is still not widely used. This endang…
Adaptive Cholesky Gaussian Processes
Simon Bartels, Kristoffer Stensbo-Smidt, Pablo Moreno-Muñoz +3
We present a method to approximate Gaussian process regression models for large datasets by considering only a subset of the data. Our approach is novel in that the size of the sub…
Bounds all around: training energy-based models with bidirectional bounds
Cong Geng, Jia Wang, Zhiyong Gao +2
Energy-based models (EBMs) provide an elegant framework for density estimation, but they are notoriously difficult to train. Recent work has established links to generative adversa…