Profile

Luca Eyring is an ELLIS PhD student in the Explainable Machine Learning Group at the Technical University of Munich and Helmholtz AI under the supervision of Zeynep Akata and Alexey Dosovitskiy (Inceptive). He is broadly interested in generative modeling, representation learning, and optimal transport.

He pursued a Bachelor in Informatics at LMU Munich and a Master specializing in Machine Learning at Technical University of Munich. During his studies, he spent time at the DLR Insitute for Data Science, BMW, and Helmholtz Munich.

Publications

"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization"
Luca Eyring *, Shyamgopal Karthik *, Karsten Roth, Alexey Dosovitskiy, Zeynep Akata
Thirty-eighth Annual Conference on Neural Information Processing Systems, NeurIPS 2024

"Disentangled Representational Learning with the Gromov-Monge Gap"
Théo Uscidda *, Luca Eyring *, Karsten Roth, Fabian Theis, Zeynep Akata, Marco Cuturi
ICML Workshop on Structured Probabilistic Inference & Generative Modeling, SPIGM @ ICML 2024

"Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation"
Luca Eyring *, Dominik Klein *, Théo Uscidda *, Giovanni Palla, Niki Kilbertus, Zeynep Akata, Fabian Theis
International Conference on Learning Representations, ICLR 2024