Niklas Schweiger
MSc Student at TU Munich · Robotics, Cognition, Intelligence
Research Assistant @ CVAI Lab
Prof. Daniel Cremers' Group, TUM
📧 niklas.schweiger@tum.de
Hi! I’m a Master’s student in Robotics, Cognition, Intelligence at the Technical University of Munich (TUM). I work on machine learning, generative models, and inference-time alignment — specifically on efficient, reward-agnostic methods to steer diffusion and flow models without fine-tuning or differentiable rewards.
I did my Bachelor’s in Electrical Engineering and Information Technology at TUM and moved into AI and machine learning during my later semesters. Before starting my Master’s, I interned at Siemens AG, where I applied ML to 3D part retrieval in industrial manufacturing. During my Master’s, I spent an exchange semester at Chalmers University of Technology in Gothenburg, Sweden.
Projects
Trust-Region Noise Search (TRS)
Publication · Black-box alignment for diffusion and flow models.
Niklas Schweiger, K. Ram, Daniel Cremers
Accepted @ ReALM-GEN Workshop, ICLR 2026.
📄 Download Paper
We propose a simple trust-region based search algorithm (TRS) which treats the pre-trained generative and reward models as black boxes, only optimizing the source noise to achieve reward-agnostic alignment.
Caire
Award · Overcoming language barriers in healthcare with AI-powered reporting.
Team: Enough Slices
🥈 2nd Place at TUM.ai Makeathon (April 2023).
Caire is an AI-powered assistant designed to automate medical reporting. Using real-time speech-to-text and a fine-tuned LLM, it extracts medically relevant information and generates structured reports.