pith. sign in

Mark Niklas M\"uller

Identifiers

  • name variant Mark Niklas M\"uller 0.60 · backfill

Papers (24)

  1. Automated Benchmark Generation for Repository-Level Coding Tasks cs.SE · 2025 · author #2
  2. Average Certified Radius is a Poor Metric for Randomized Smoothing cs.LG · 2024 · author #3
  3. Diagnosing Robotics Systems Issues with Large Language Models cs.CL · 2024 · author #4
  4. Mitigating Catastrophic Forgetting in Language Transfer via Model Merging cs.LG · 2024 · author #3
  5. SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents cs.SE · 2024 · author #2
  6. ConStat: Performance-Based Contamination Detection in Large Language Models cs.CL · 2024 · author #2
  7. DAGER: Exact Gradient Inversion for Large Language Models cs.LG · 2024 · author #4
  8. Gaussian Loss Smoothing Enables Certified Training with Tight Convex Relaxations cs.LG · 2024 · author #2
  9. SPEAR:Exact Gradient Inversion of Batches in Federated Learning cs.LG · 2024 · author #3
  10. Evading Data Contamination Detection for Language Models is (too) Easy cs.LG · 2024 · author #2
  11. Automated Classification of Model Errors on ImageNet cs.CV · 2023 · author #2
  12. Prompt Sketching for Large Language Models cs.CL · 2023 · author #2
  13. Expressivity of ReLU-Networks under Convex Relaxations cs.LG · 2023 · author #2
  14. Understanding Certified Training with Interval Bound Propagation cs.LG · 2023 · author #2
  15. TAPS: Connecting Certified and Adversarial Training cs.LG · 2023 · author #2
  16. Efficient Certified Training and Robustness Verification of Neural ODEs cs.LG · 2023 · author #2
  17. First Three Years of the International Verification of Neural Networks Competition (VNN-COMP) cs.LG · 2023 · author #2
  18. The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Results cs.LG · 2022 · author #1
  19. Certified Training: Small Boxes are All You Need cs.LG · 2022 · author #1
  20. (De-)Randomized Smoothing for Decision Stump Ensembles cs.LG · 2022 · author #2
  21. Robust and Accurate -- Compositional Architectures for Randomized Smoothing cs.LG · 2022 · author #2
  22. Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks cs.LG · 2021 · author #1
  23. Boosting Randomized Smoothing with Variance Reduced Classifiers cs.LG · 2021 · author #2
  24. PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations cs.AI · 2021 · author #1

Mentions

  • 2301.05815 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2403.07095 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2410.06895 #3 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2503.07701 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2406.12952 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2403.03945 #3 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2405.15586 #4 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2410.09084 #4 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2407.08699 #3 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2405.16281 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2306.10426 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2402.02823 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2401.02430 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2311.04954 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2311.04015 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2305.04574 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2110.08260 #1 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2303.05246 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2210.04871 #1 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2212.10376 #1 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2205.13909 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2204.00487 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2106.06946 #2 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller
  • 2103.03638 #1 · arxiv_oai · confidence 0.70 Mark Niklas M\"uller

Frequent Coauthors