collaborators

7 papers

cs.CV2026

Sparse Concept Channels in Frozen 3D CT Vision Encoders

Farhad Nooralahzadeh, Lea Bogensperger, Christian Bluethgen +1

Large vision-language models are becoming increasingly dominant in 3D medical image interpretation, but we rarely know <i>which</i> internal units encode clinical findings or <i>wh…

cs.CV2026

Understanding, Accelerating, and Improving MeanFlow Training

Jin-Young Kim, Hyojun Go, Lea Bogensperger +5

MeanFlow promises high-quality generative modeling in few steps, by jointly learning instantaneous and average velocity fields. Yet, the underlying training dynamics remain unclear…

cs.LG2026

Generating Physically Consistent Molecules with Energy-Based Models

Christoph Griesbacher, Lea Bogensperger, Andreas Habring +1

Molecules in equilibrium follow a Boltzmann distribution, making the underlying energy landscape a physically grounded modeling objective. However, such landscapes are difficult to…

cs.LG2026

Repurposing Protein Language Models for Latent Flow-Based Fitness Optimization

Amaru Caceres Arroyo, Lea Bogensperger, Ahmed Allam +3

Protein fitness optimization is challenged by a vast combinatorial landscape where high-fitness variants are extremely sparse. Many current methods either underperform or require c…

math.OC2025

An Adaptively Inexact Method for Bilevel Learning Using Primal-Dual Style Differentiation

Lea Bogensperger, Matthias J. Ehrhardt, Thomas Pock +2

We consider a bilevel learning framework for learning linear operators. In this framework, the learnable parameters are optimized via a loss function that also depends on the minim…

cs.LG2025

A Variational Perspective on Generative Protein Fitness Optimization

Lea Bogensperger, Dominik Narnhofer, Ahmed Allam +2

The goal of protein fitness optimization is to discover new protein variants with enhanced fitness for a given use. The vast search space and the sparsely populated fitness landsca…