Mark Niklas Müller

53 papers A* 18Journal 33Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?
CoRR
Thibaud Gloaguen, Niels Mündler, Mark Niklas Müller, Veselin Raychev, Martin T. Vechev
2025 A* conf
Automated Benchmark Generation for Repository-Level Coding Tasks.
ICML
Konstantinos Vergopoulos, Mark Niklas Müller, Martin T. Vechev
2025 J jnl
Automated Benchmark Generation for Repository-Level Coding Tasks.
CoRR
Konstantinos Vergopoulos, Mark Niklas Müller, Martin T. Vechev
2025 A* conf
Average Certified Radius is a Poor Metric for Randomized Smoothing.
ICML
Chenhao Sun, Yuhao Mao, Mark Niklas Müller, Martin T. Vechev
2025 A* conf
Certification for Differentially Private Prediction in Gradient-Based Training.
ICML
Matthew Wicker, Philip Sosnin, Igor Shilov, Adrianna Janik, Mark Niklas Müller, Yves-Alexandre de Montjoye, Adrian Weller, Calvin Tsay
2025 J jnl
Certified Robustness to Data Poisoning in Gradient-Based Training.
Trans. Mach. Learn. Res.
Philip Sosnin, Mark Niklas Müller, Maximilian Baader, Calvin Tsay, Matthew Wicker
2025 J jnl
Gaussian Loss Smoothing Enables Certified Training with Tight Convex Relaxations.
Trans. Mach. Learn. Res.
Stefan Balauca, Mark Niklas Müller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin T. Vechev
2024 J jnl
Automated Classification of Model Errors on ImageNet.
CoRR
Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2024 J jnl
Average Certified Radius is a Poor Metric for Randomized Smoothing.
CoRR
Chenhao Sun, Yuhao Mao, Mark Niklas Müller, Martin T. Vechev
2024 J jnl
Certificates of Differential Privacy and Unlearning for Gradient-Based Training.
CoRR
Matthew Wicker, Philip Sosnin, Adrianna Janik, Mark Niklas Müller, Adrian Weller, Calvin Tsay
2024 J jnl
Certified Robustness to Data Poisoning in Gradient-Based Training.
CoRR
Philip Sosnin, Mark Niklas Müller, Maximilian Baader, Calvin Tsay, Matthew Wicker
2024 J jnl
Code Agents are State of the Art Software Testers.
CoRR
Niels Mündler, Mark Niklas Müller, Jingxuan He, Martin T. Vechev
2024 A* conf
ConStat: Performance-Based Contamination Detection in Large Language Models.
NeurIPS
Jasper Dekoninck, Mark Niklas Müller, Martin T. Vechev
2024 J jnl
ConStat: Performance-Based Contamination Detection in Large Language Models.
CoRR
Jasper Dekoninck, Mark Niklas Müller, Martin T. Vechev
2024 A* conf
DAGER: Exact Gradient Inversion for Large Language Models.
NeurIPS
Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin T. Vechev
2024 J jnl
DAGER: Exact Gradient Inversion for Large Language Models.
CoRR
Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin T. Vechev
2024 J jnl
Diagnosing Robotics Systems Issues with Large Language Models.
CoRR
Jordis Emilia Herrmann, Aswath Mandakath Gopinath, Mikael Norrlof, Mark Niklas Müller
2024 J jnl
Evading Data Contamination Detection for Language Models is (too) Easy.
CoRR
Jasper Dekoninck, Mark Niklas Müller, Maximilian Baader, Marc Fischer, Martin T. Vechev
2024 A* conf
Expressivity of ReLU-Networks under Convex Relaxations.
ICLR
Maximilian Baader, Mark Niklas Müller, Yuhao Mao, Martin T. Vechev
2024 — conf
Mitigating Catastrophic Forgetting in Language Transfer via Model Merging.
EMNLP (Findings)
Anton Alexandrov, Veselin Raychev, Mark Niklas Müller, Ce Zhang, Martin T. Vechev, Kristina Toutanova
2024 J jnl
Mitigating Catastrophic Forgetting in Language Transfer via Model Merging.
CoRR
Anton Alexandrov, Veselin Raychev, Mark Niklas Müller, Ce Zhang, Martin T. Vechev, Kristina Toutanova
2024 J jnl
Overcoming the Paradox of Certified Training with Gaussian Smoothing.
CoRR
Stefan Balauca, Mark Niklas Müller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin T. Vechev
2024 A* conf
Prompt Sketching for Large Language Models.
ICML
Luca Beurer-Kellner, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2024 A* conf
SPEAR: Exact Gradient Inversion of Batches in Federated Learning.
NeurIPS
Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin T. Vechev
2024 J jnl
SPEAR: Exact Gradient Inversion of Batches in Federated Learning.
CoRR
Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Müller, Martin T. Vechev
2024 A* conf
SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents.
NeurIPS
Niels Mündler, Mark Niklas Müller, Jingxuan He, Martin T. Vechev
2024 — —
Training and Certification of Neural Networks with Guarantees.
Mark Niklas Müller
2024 A* conf
Understanding Certified Training with Interval Bound Propagation.
ICLR
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2023 J jnl
Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks.
Proc. ACM Program. Lang.
Mark Niklas Müller, Marc Fischer, Robin Staab, Martin T. Vechev
2023 A* conf
Automated Classification of Model Errors on ImageNet.
NeurIPS
Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2023 A* conf
Certified Training: Small Boxes are All You Need.
ICLR
Mark Niklas Müller, Franziska Eckert, Marc Fischer, Martin T. Vechev
2023 A* conf
Connecting Certified and Adversarial Training.
NeurIPS
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2023 A* conf
Efficient Certified Training and Robustness Verification of Neural ODEs.
ICLR
Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2023 J jnl
Efficient Certified Training and Robustness Verification of Neural ODEs.
CoRR
Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2023 J jnl
Expressivity of ReLU-Networks under Convex Relaxations.
CoRR
Maximilian Baader, Mark Niklas Müller, Yuhao Mao, Martin T. Vechev
2023 J jnl
First Three Years of the International Verification of Neural Networks Competition (VNN-COMP).
CoRR
Christopher Brix, Mark Niklas Müller, Stanley Bak, Taylor T. Johnson, Changliu Liu
2023 J jnl
First three years of the international verification of neural networks competition (VNN-COMP).
Int. J. Softw. Tools Technol. Transf.
Christopher Brix, Mark Niklas Müller, Stanley Bak, Taylor T. Johnson, Changliu Liu
2023 J jnl
Prompt Sketching for Large Language Models.
CoRR
Luca Beurer-Kellner, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2023 J jnl
TAPS: Connecting Certified and Adversarial Training.
CoRR
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2023 J jnl
Understanding Certified Training with Interval Bound Propagation.
CoRR
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2022 A* conf
(De-)Randomized Smoothing for Decision Stump Ensembles.
NeurIPS
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2022 J jnl
(De-)Randomized Smoothing for Decision Stump Ensembles.
CoRR
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2022 A* conf
Boosting Randomized Smoothing with Variance Reduced Classifiers.
ICLR
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2022 J jnl
Certified Training: Small Boxes are All You Need.
CoRR
Mark Niklas Müller, Franziska Eckert, Marc Fischer, Martin T. Vechev
2022 A* conf
Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound.
ICLR
Claudio Ferrari, Mark Niklas Müller, Nikola Jovanovic, Martin T. Vechev
2022 J jnl
Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound.
CoRR
Claudio Ferrari, Mark Niklas Müller, Nikola Jovanovic, Martin T. Vechev
2022 J jnl
PRIMA: general and precise neural network certification via scalable convex hull approximations.
Proc. ACM Program. Lang.
Mark Niklas Müller, Gleb Makarchuk, Gagandeep Singh, Markus Püschel, Martin T. Vechev
2022 J jnl
Robust and Accurate - Compositional Architectures for Randomized Smoothing.
CoRR
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2022 J jnl
The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Results.
CoRR
Mark Niklas Müller, Christopher Brix, Stanley Bak, Changliu Liu, Taylor T. Johnson
2021 J jnl
Boosting Randomized Smoothing with Variance Reduced Classifiers.
CoRR
Miklós Z. Horváth, Mark Niklas Müller, Marc Fischer, Martin T. Vechev
2021 A* conf
Certify or Predict: Boosting Certified Robustness with Compositional Architectures.
ICLR
Mark Niklas Müller, Mislav Balunovic, Martin T. Vechev
2021 J jnl
Effective Certification of Monotone Deep Equilibrium Models.
CoRR
Mark Niklas Müller, Robin Staab, Marc Fischer, Martin T. Vechev
2021 J jnl
Precise Multi-Neuron Abstractions for Neural Network Certification.
CoRR
Mark Niklas Müller, Gleb Makarchuk, Gagandeep Singh, Markus Püschel, Martin T. Vechev