MM

Mark Niklas Müller

0000-0002-2496-6542

cs.LGcs.AIcs.SEcs.CRcs.CLcs.CVcs.DCcs.RO

On Valency

published · living versions

PROBE: Frontier Coding Agents Find Different Bugs Than Maintainers Fix

with Marco Paina, Niels Mündler-Sasahara, Martin Vechev

1 version

W_6v7x34v3v1 · current

Preprints & journals

29 papers in the corpus · 2021–2026

TestSuiteBench: Coding Agents Struggle to Generate Strong Test Suites from Specifications

Kazuki Egashira, Niels Mundler-Sasahara, Mark Niklas Muller et al.

0 citations

2610.13065v12026arXiv

Coding Agents Don't Know When to Act

Thibaud Gloaguen, Niels Mundler, Mark Muller et al.

0 citations

2605.07769v12026arXiv

Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?

Thibaud Gloaguen, Niels Mundler-Sasahara, Mark Niklas Muller et al.

1 citation

2602.11988v32026arXiv

Automated Benchmark Generation for Repository-Level Coding Tasks

Konstantinos Vergopoulos, Mark Niklas Muller, Martin Vechev

0 citations

2503.07701v12025arXiv

Average Certified Radius is a Poor Metric for Randomized Smoothing

Chenhao Sun, Yuhao Mao, Mark Niklas Muller et al.

0 citations

2410.06895v42024arXiv

Diagnosing Robotics Systems Issues with Large Language Models

Jordis Emilia Herrmann, Aswath Mandakath Gopinath, Mikael Norrlof et al.

0 citations

2410.09084v12024arXiv

Mitigating Catastrophic Forgetting in Language Transfer via Model Merging

Anton Alexandrov, Veselin Raychev, Mark Niklas Muller et al.

6 citations

2407.08699v22024arXiv

Certification for Differentially Private Prediction in Gradient-Based Training

Matthew Wicker, Philip Sosnin, Igor Shilov et al.

1 citation

2406.13433v32024arXiv

SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents

Niels Mundler, Mark Niklas Muller, Jingxuan He et al.

20 citations

2406.12952v32024arXiv

Certified Robustness to Data Poisoning in Gradient-Based Training

Philip Sosnin, Mark N. Muller, Maximilian Baader et al.

0 citations

2406.05670v32024arXiv

ConStat: Performance-Based Contamination Detection in Large Language Models

Jasper Dekoninck, Mark Niklas Muller, Martin Vechev

9 citations

2405.16281v12024arXiv

DAGER: Exact Gradient Inversion for Large Language Models

Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader et al.

12 citations

2405.15586v22024arXiv

Gaussian Loss Smoothing Enables Certified Training with Tight Convex Relaxations

Stefan Balauca, Mark Niklas Muller, Yuhao Mao et al.

0 citations

2403.07095v42024arXiv

SPEAR:Exact Gradient Inversion of Batches in Federated Learning

Dimitar I. Dimitrov, Maximilian Baader, Mark Niklas Muller et al.

7 citations

2403.03945v32024arXiv

Evading Data Contamination Detection for Language Models is (too) Easy

Jasper Dekoninck, Mark Niklas Muller, Maximilian Baader et al.

4 citations

2402.02823v22024arXiv

Automated Classification of Model Errors on ImageNet

Momchil Peychev, Mark Niklas Muller, Marc Fischer et al.

1 citation

2401.02430v12023arXiv

Prompt Sketching for Large Language Models

Luca Beurer-Kellner, Mark Niklas Muller, Marc Fischer et al.

0 citations

2311.04954v12023arXiv

Expressivity of ReLU-Networks under Convex Relaxations

Maximilian Baader, Mark Niklas Muller, Yuhao Mao et al.

0 citations

2311.04015v12023arXiv

TAPS: Connecting Certified and Adversarial Training

Yuhao Mao, Mark Niklas Muller, Marc Fischer et al.

0 citations

2305.04574v22023arXiv

Efficient Certified Training and Robustness Verification of Neural ODEs

Mustafa Zeqiri, Mark Niklas Muller, Marc Fischer et al.

0 citations

2303.05246v12023arXiv

First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)

Christopher Brix, Mark Niklas Muller, Stanley Bak et al.

69 citations

2301.05815v12023International Journal on Software Tools for Technology Transfer, 25 (2023) 329-339

The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Results

Mark Niklas Muller, Christopher Brix, Stanley Bak et al.

27 citations

2212.10376v22022arXiv

Certified Training: Small Boxes are All You Need

Mark Niklas Muller, Franziska Eckert, Marc Fischer et al.

10 citations

2210.04871v22022arXiv

(De-)Randomized Smoothing for Decision Stump Ensembles

Mikl'os Z. Horv'ath, Mark Niklas Muller, Marc Fischer et al.

2 citations

2205.13909v22022arXiv

Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound

Claudio Ferrari, Mark Niklas Muller, Nikola Jovanovic et al.

27 citations

2205.00263v12022arXiv

Robust and Accurate -- Compositional Architectures for Randomized Smoothing

Mikl'os Z. Horv'ath, Mark Niklas Muller, Marc Fischer et al.

1 citation

2204.00487v12022arXiv

Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks

Mark Niklas Muller, Marc Fischer, Robin Staab et al.

5 citations

2110.08260v22021arXiv

Boosting Randomized Smoothing with Variance Reduced Classifiers

Mikl'os Z. Horv'ath, Mark Niklas Muller, Marc Fischer et al.

7 citations

2106.06946v32021arXiv

PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations

Mark Niklas Muller, Gleb Makarchuk, Gagandeep Singh et al.

77 citations

2103.03638v32021Proceedings of the ACM on Programming Languages, Volume 6, Issue POPL, January 2022, Article No.: 43, pp 1-33

Career total: 53 works. 29 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.