Curriculum Vitae

Tobias Ladner joined the Cyber-Physical-Systems Group as a Ph.D. candidate under the supervision of Prof. Dr.-Ing. Matthias Althoff in 2022. Tobias has received both, his master's degree and his bachelor's degree in Informatics from the Technical University of Munich in 2021 and 2019, respectively.

His research interests include AI safety with a focus on the formal verification of neural networks and cyber-physical systems, ensuring that AI systems perform reliably in safety-critical applications. Examples of his research are listed under publications below and at: https://cora.in.tum.de/pages/neural-networks/ . All publications are also available on Google Scholar.

Tobias is the current administrator of the toolbox CORA: https://cora.in.tum.de/. He is also a member of the DFG-funded project “Formal Verification of Analog AI Hardware (FAI)“. Personal website: https://toladner.github.io/.

Offered Thesis Topics

I am always looking for self-motivated students who want to work in my research area. If you are interested in writing your thesis in the field of my research, please write me an email containing your CV, transcript of records, and a rough direction you are interested in. Check the thesis proposals and practical course topics below for examples.

Available Topics:

• Just send me an email ;)

Ongoing:

• [GR] Towards Provable Safety in Railway Video Monitoring
• [GR] Towards Verified Fairness: Certifying Robustness in Language Models
• [MT] Set-Based Learning of Neural Barrier Certificates for Safety Verification of Dynamic Systems

Finished:

• [MT] Anomaly Detection for Semi-Supervised 3D Object Detection (coop. w/ SETLabs Research)
• [BT] Towards Formal Verification of Large Language Models: Applying Reachability Analysis on Transformers
• [MT] Enabling Formal Verification of Data-Aware Hardware Models (coop. w/ Apple)
• [BT] Analysis of Neural Activation Patterns During Video Segmentation for Formal Verification
• [BT] Robust Reinforcement Learning using Set-Based Training
• [MT] Automatic Abstraction Refinement for the Verification of Neural Network Control Systems
• [MT] Co-Design for Training and Verifying Neural Networks
• [BT] Set-Based Modeling of Ambiguous Word Embeddings using Deep Learning
• [BT] Formal Verification of Robust Neural Networks using Reachability Analysis

Teaching

Practical Course –  Formal Methods for AI-Enabled Cyber-Physical Systems (IN2106)
[SoSe 25] [SoSe 24] [SoSe 23] [SoSe 22]
[WiSe 24/25] [WiSe 23/24] [WiSe 22/23] 

• Implementation of algorithms for formal neural network verification in CORA
• Selected topics: Topics
   

Seminar – Cyber-Physical Systems (IN0014, IN2107, IN4813)
[SoSe 25] [SoSe 24] [SoSe 23]
[WiSe 24/25] [WiSe 22/23]

• Literature research on formal verification of neural networks
• Selected topics: Topics, Topics
   

Lecture – Formal Methods for Cyber-Physical Systems (IN2383)
[WiSe 24/25] [WiSe 23/24] [WiSe 22/23]

• Fundamentals of set-based computing and formal verification of neural network