Till Richter
Ph.D. Student in Machine Learning for Computational Biology
Technical University of Munich
Helmholtz Munich
I am a MUDS Ph.D. student in Machine Learning for Computational Biology at TUM and Helmholtz Munich, advised by Fabian Theis, Niki Kilbertus, and Yoshua Bengio. My research focuses on self-supervised learning, generative models, and dynamical systems in single-cell genomics. I collaborate with the Causal Cell Dynamics Lab at Helmholtz Munich and MILA Montreal, working on methods to uncover meaningful structure in biological data, and I’m part of the MCML and MDSI.
My goal is to make machine learning models of biological data more reliable and scalable across modalities. To achieve this goal, my research has been focused on self-supervised learning, generative models, and neural differential equations to model single-cell transcriptomics. Besides the application, I am also interested in the methodological foundations.
Beyond research, I enjoy teaching and mentoring students. I have co-organized workshops at ICLR and ECCB and regularly teach courses on machine learning and deep learning. I also have a strong interest in entrepreneurship—through the Manage&More scholarship at UnternehmerTUM, I have gained hands-on experience in innovation-driven projects at the intersection of AI and industry.
I am always happy to discuss research, collaborations, or applications of AI in biology. Feel free to reach out!
news
| May 12, 2025 |  Today marks the beginning of my research internship at Microsoft Research in Cambridge, MA! I’m excited to work with Lorin Crawford and the team on cutting-edge research projects. |
|---|---|
| Apr 28, 2025 |  Our paper Interpretable Self-Supervised Prototype Learning for Single-Cell Transcriptomics was presented at the LMRL Workshop at ICLR 2025! The work introduces scProto, a novel method that learns interpretable prototypes for denoising single-cell data while preserving biological structure and removing batch effects. Link |
| Apr 28, 2025 |  The Learning Meaningful Representations of Life (LMRL) Workshop I co-organized at ICLR 2025 in Singapore was a great success! The workshop brought together researchers working on foundation models for biological data, multimodal representation learning, and multiscale biological representations, featuring exciting keynotes from leaders in the field and stimulating discussions about the future of AI in biology. s |
| Jan 22, 2025 | CFGen: Generating Multi-Modal and Multi-Attribute Single-Cell Counts has been accepted at ICLR 2025! Link |
| Dec 27, 2024 | Our paper Delineating the Effective Use of Self-Supervised Learning in Single-Cell Genomics is now published in Nature Machine Intelligence! Link |
| Dec 25, 2024 | Excited to share that I will be joining Microsoft Research in Cambridge, MA, working with Lorin Crawford as a research intern from May to August 2025! |
| Dec 10, 2024 | Our collaborative paper Heterogeneity-driven phenotypic plasticity and treatment response in branched-organoid models of pancreatic ductal adenocarcinoma has been published in Nature Biomedical Engineering! Link |
| Dec 03, 2024 | The Learning Meaningful Representations of Life (LMRL) Workshop I co-organize got accepted at ICLR 2025! Link |