About me

Since July 2024, I am pursuing a Ph.D. at the Secure, Reliable, and Intelligent Systems Lab at ETH Zürich, advised by Prof. Martin Vechev. My research focuses on enhancing the reliability and security of Large Language Models, with an emphasis on ensuring the faithfulness and correctness of generated text and code. Previously, I worked on the formal verification of data structures and algorithms and co-founded a start-up specializing in Smart Contracts.

If you are interested in conducting a research project, BSc Thesis or MSc Thesis at SRI, I am looking for motivated students with a strong background in programming languages and formal methods. Feel free to contact me about this via e-mail. I am open to new project ideas. Some suggestions around formal methods for Large Language Models include:

Publications

2025

Constrained Decoding of Diffusion LLMs with Context-Free Grammars
Niels Mündler, Jasper Dekoninck, Martin Vechev
arXiv 2025
BaxBench: Can LLMs Generate Secure and Correct Backends?
Mark Vero, Niels Mündler, Victor Chibotaru, Veselin Raychev, Maximilian Baader, Nikola Jovanović, Jingxuan He, Martin Vechev
ICML 2025 Spotlight
Black-Box Adversarial Attacks on LLM-Based Code Completion
Slobodan Jenko*, Niels Mündler*, Jingxuan He, Mark Vero, Martin Vechev
ICML 2025 * Equal contribution
Type-Constrained Code Generation with Language Models
Niels Mündler, Jingxuan He, Hao Wang, Koushik Sen, Dawn Song, Martin Vechev
PLDI 2025 † Co-leadership

2024

SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
Niels Mündler, Mark Niklas Müller, Jingxuan He, Martin Vechev
NeurIPS 2024

Work experience

  • ETH Zurich, January - June 2024
    Research Associate at SRI Lab
  • OpenSwap Technologies AG, 2021 - 2023
    Co-Founder and CTO

Education

  • ETH Zurich, October 2021 - December 2023
    M.Sc. Computer Science
  • National University of Singapore, August 2019 - January 2020
    Exchange Student at School of Computing
  • TU Munich, October 2017 - March 2021
    B.Sc. Computer Science

Awards

  • ICTAC 2021, Best Paper Award for "A Verified Imperative Implementation of B+-Trees in Isabelle"
  • BWINF 2016, Second place at German national informatics contest