Marie Brockschmidt

News

Jul 2026 Attending ICML 2026 in Seoul, South Korea.
Jun 2026 Presented SurvDiff as a talk at the Helmholtz AI Conference (HAICON26), Munich.
May 2026 New preprint: ConfoundingSHAP, a Shapley-based method for quantifying confounding strength in causal inference.
May 2026 New preprint: Amortizing Causal Sensitivity Analysis via Prior Data-Fitted Networks.
Apr 2026 SurvDiff accepted at ICML 2026 as a spotlight paper, top 2.2% of all 24,000+ submissions.
Sep 2025 New preprint: SurvDiff, a diffusion model for synthetic data generation in survival analysis.
Jun 2025 Started my PhD at LMU Munich under the supervision of Stefan Feuerriegel.

Publications

First author

SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis

Marie Brockschmidt, Maresa Schröder, Stefan Feuerriegel

ICML 2026 Spotlight · top 2.2%

[paper] [code]

ConfoundingSHAP: Quantifying Confounding Strength in Causal Inference

Marie Brockschmidt, Santo M.A.R. Thies, Maresa Schröder, Dennis Frauen, Valentyn Melnychuk, Maximilian Muschalik, Eyke Hüllermeier, Stefan Feuerriegel

Preprint 2026

[paper]

Contributed

co-author

Amortizing Causal Sensitivity Analysis via Prior Data-Fitted Networks

Emil Javurek, Dennis Frauen, Marie Brockschmidt, Jonas Schweisthal, Stefan Feuerriegel

Preprint 2026

[paper]

co-author

Causal Methods for LLM Development and Evaluation

Dennis Frauen, Marie Brockschmidt, Konstantin Hess, Haorui Ma, Yuchen Ma, Abdurahman Maarouf, Maresa Schröder, Jonas Schweisthal, Yuxin Wang, Atreya Deviyani, Sonali Parbhoo, Rahul G. Krishnan, Stefan Feuerriegel

KDD 2026

[paper]

Impressum · Marie Brockschmidt · Ludwigstr. 28 RG, 80539 München · marie.brockschmidt [at] lmu [dot] de