works on

From the 1 of 23 linked papers with an AI index.

activity
20242026
most citedMolMiner: Toward Controllable, 3D-Aware, Fragment-Based Molecular Design

1 citations · 2 across the 5 of their papers we have counts for

collaborators

23 papers

cs.LG20261 cited

MolMiner: Toward Controllable, 3D-Aware, Fragment-Based Molecular Design

Raul Ortega-Ochoa, Tejs Vegge, Jes Frellsen

MolMiner is an autoregressive model that builds molecules by attaching fragments in a geometry‑aware, symmetry‑respecting way, while allowing users to control multiple physicochemi…

cs.IR20261 cited

Normative Alignment of Recommender Systems via Internal Label Shift

Johannes Kruse, Kasper Lindskow, Michael Riis Andersen +4

We introduce NAILS (Normative Alignment of Recommender Systems via Internal Label Shift), a simple and scalable method for aligning recommendation outputs with target distributions…

cs.IR2026

ZoRRO: A Zero-Weight Personalized Recommender System for Scalable News Recommendation

Johannes Kruse, Ryotaro Shimizu, Kasper Lindskow +4

We present ZoRRO (Zero-Weight Personalized Recommender System), a zero-weight, training-free framework for personalized news recommendation designed for scalable real-world deploym…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…