My name is Elvis, I co-founded mimic, a Zurich-based startup working on scalable AI models for robotic manipulation. We raised over $20M in funding from leading VCs and grants.
Previously, I completed my PhD in Machine Learning at ETH Zurich as a Doctoral Fellow at the ETH AI Center, part of Prof. Benjamin Grewe’s group at the Institute of Neuroinformatics and Prof. Robert Katzschmann’s Soft Robotics Lab. I received a Master’s in Data Science at ETH Zurich and a Bachelor’s in Computer Science at the University of Milan. I was also an intern at Oracle Labs.
Research
At mimic we are developing recipes for scalable training of generative models of robotic behaviors, and run these models on our own robotic hand hardware.
During my PhD, I worked on Meta-Learning, Multimodality and Robotics. My research focused on how sample-efficient learning architectures, pre-training and multi-modal conditioning can be leveraged to train agents that solve complex task such as dexterous robotic manipulation. I have broadly been interested in methods for extracting knowledge from pre-trained foundation models that can be useful for training downstream agents - see recent work on repurposing Vision-Language Models as reward functions. I also worked on an application of Diffusion Models for generating neural network parameters (because, why not?).
I previously did theoretical research in Batched Bayesian Optimization with Determinantal Point Processes - the kind of research involving proofs of Bayesian bounds on regret. I also worked on neural network-based Differentiable Simulation of a Soft Robotic Fish.
See here a complete list of my publications.
Other Stuff
Learn more about me here. For my hot takes and reading recommendations on deep learning and miscellaneous topics, see my links page.
Contact
You can send me an email at elvis dot nava at mimicrobotics dot com or DM me on Twitter @elvisnavah.
Latest News
December 2025: We published “mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs”, a new class of Video-Action Model that replaces the VLM backbone of traditional VLAs with a video model, allowing us to leverage pure video pre-training for robot learning.
December 2025: I successfully defended my PhD at ETH Zurich. I thank all my friends and collaborators at the ETH AI Center, the Institute of Neuroinformatics and the Soft Robotics Lab.
November 2025: I was interviewed by Enrico Pagliarini for Radio24’s “2024” program, where I talked about mimic and its approach towards general purpose automation.