Michael Piseno

X / Github / CV

Bio

I work on systems for robotic intelligence. I am interested in loco-manipulation with humanoids, VLA foundation models, and control theory.

I am a PhD student in Computer Science at Stanford University. I completed my MS at Stanford advised by Karen Liu where I worked on diffusion models for physics-based character animation. I spent time as a visiting researcher in the Hybrid Robotics Lab at UC Berkeley advised by Koushil Sreenath and at DeepMind working on learning natural locomotion controllers under Atil Iscen. My research is supported by the National Defense Science and Engineering Graduate (NDSEG) Fellowship.

Publications

  1. Michael Piseno, Zhongyu Li, Alejandro Escontrela, Pieter Abbeel, Koushil Sreenath, Xue Bin Peng, Atil Iscen. Stylized Locomotion Control for Bipedal Humanoid Robots with Adversarial Motion Priors. 2025. (Under Review) [ site ]
  2. Takara E. Truong, Michael Piseno, Zhaoming Xie, and C. Karen Liu. PDP: Physics-Based Character Animation via Diffusion Policy. SIGGRAPH Asia, 2024. [ paper / site ]

Miscellaneous

Notes on Backpropagation in Convolutional Layers