Berat Mert Albaba
Berat Mert Albaba is a PhD student at ETH Zürich and the Max Planck Institute for Intelligent Systems, co-advised by Michael Black and Andreas Krause. His research focuses on reinforcement learning, imitation learning, and generative models for humanoid robotics and character simulation. He is best known for developing VioLA, a generalist humanoid control policy that learns from human motion data, and NIL, an imitation learning approach leveraging pretrained video diffusion models.
“VioLA's core innovation is using pretrained motion encoders that map both human and robot motion into the same latent space, allowing human video recordings to directly supervise a robot policy's action outputs.”
Source→“Lead author, ETH Zürich / MPI-IS / Vesoma. Conducted work during internship at Vesoma. Co-lead on the project.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.