works on

From the 1 of 19 linked papers with an AI index.

activity
20242026
collaborators

19 papers

stat.CO2026

Higher-Order Hit-&-Run Samplers for Linearly Constrained Densities

Richard D. Paul, Anton Stratmann, Johann F. Jadebeck +4

The paper introduces a new MCMC algorithm that combines higher‑order information (gradients and curvature of the log‑density) with Hit‑and‑Run proposals to efficiently sample distr…

cs.LG2026

RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data

Xuan Zhao, Lena Krieger, Zhuo Cao +3

Counterfactual explanations (CFs) help understand machine learning models by identifying minimal input changes that would lead to alternative model outcomes. Recent work demonstrat…

cs.AI2026

Residual-Space Evolutionary Optimization via Flow-based Generative Models

Zhuo Cao, Lena Krieger, Fernanda Nader +3

Data editing with generative methods typically requires differentiable objectives and gradient-based search. However, these assumptions break down in flow-based settings, where edi…

q-bio.QM2026

DART: A design-aware microfluidic chip paradigm for real-time live-cell image analysis

Johannes Seiffarth, Matthias Pesch, Lukas Scholtes +3

High-throughput microfluidic live-cell imaging generates rich single-cell data. Yet semi-automated procedures for locating regions of interest (RoIs), each containing one cell popu…

cs.LG2026

Counterfactual Transport Flows for Offline Conservative Trajectory Refinement

Lena Krieger, Xuan Zhao, Zhuo Cao +3

Offline reinforcement learning (RL) offers a path to policy improvement from logged data alone, using historical returns or other measurable outcomes as world feedback. A key diffi…

cs.CV2026

Self-Supervised Learning Based on Transformed Image Reconstruction for Equivariance-Coherent Feature Representation

Qin Wang, Alessio Quercia, Benjamin Bruns +3

Self-supervised learning (SSL) methods have achieved remarkable success in learning image representations allowing invariances in them - but therefore discarding transformation inf…