$ cat research_statement.txt

My research focuses on building generalist robots by combining deep generative models, 3D robot learning, learning from video, and optimization. I believe this goal can only be achieved by developing novel strategies to scale the available data for robotics and finding new algorithmic and architectural elements to enhance generalization.

Across my projects, a core theme has been learning structured representations for robot manipulation — from energy-based policies and diffusion fields to equivariant flow matching and stable dynamical systems on Lie groups.

$ ls -lt ./publications/
01
A Survey on Deep Generative Models for Robot Learning from Multimodal Demonstrations
TRO 2025
Julen Urain, Ajay Mandlekar, Yilun Du, Nur Muhammad Mahi Shafiullah, Danfei Xu, Katerina Fragkiadaki, Georgia Chalvatzaki, Jan Peters
A comprehensive survey on deep generative models for robot learning from multimodal demonstrations, covering diffusion models, energy-based models, normalizing flows, and their applications to manipulation, locomotion, and dexterous control.
02
Noise-conditioned Energy-based Annealed Rewards (NEAR)
ICLR 2025
Aamodh Diwan, Julen Urain, Jens Kober, Jan Peters
A generative framework for imitation learning from observation that uses noise-conditioned energy-based models with annealed rewards to learn robust policies without access to expert actions.
03
Actionflow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matching BEST PAPER
PRE-PRINT 2024
Niklas Funk, Julen Urain, Joao Carvalho, Vignesh Prasad, Georgia Chalvatzaki, Jan Peters
Proposes equivariant flow matching for robot policy learning that leverages spatial symmetries to achieve accurate and efficient manipulation policies. Won Best Paper Award at the Structural Priors as Inductive Biases for Learning Robot Dynamics workshop at RSS 2024.
04
PianoMime: Learning a Generalist, Dexterous Piano Player from Internet Demonstrations
CORL 2024
Cheng Qian, Julen Urain, Kevin Zakka, Jan Peters
A framework for learning dexterous piano playing from internet video demonstrations, enabling a robotic hand to perform complex musical pieces through generalist imitation learning.
05
SE(3)-DiffusionFields: Learning Smooth Cost Functions for Joint Grasp and Motion Optimization through Diffusion BEST PAPER
ICRA 2023
Julen Urain, Niklas Funk, Georgia Chalvatzaki, Jan Peters
Introduces diffusion models on SE(3) for learning smooth cost functions that jointly optimize grasp poses and motion trajectories. Won Best Paper Award at the Geometric Representations Workshop at ICRA 2023.
06
Learning Stable Vector Fields on Lie Groups
RA-L / ICRA 2022
Julen Urain, Davide Tateo, Jan Peters
Proposes a method for learning stable dynamical systems on Lie groups, enabling robots to generate stable orientation-aware motions with guaranteed convergence properties.
07
Learning Implicit Priors for Motion Optimization
IROS 2022
Julen Urain, An T. Le, Alexander Lambert, Georgia Chalvatzaki, Byron Boots, Jan Peters
Introduces implicit neural representations as priors for trajectory optimization, enabling efficient motion planning that combines learned cost landscapes with optimization-based control.
08
Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning
R:SS / IJRR 2021
Julen Urain, Anqi Li, Puze Liu, Carlo D'Eramo, Jan Peters
Proposes composable energy-based policies for reactive robot motion generation, where multiple energy functions can be combined to achieve complex behaviors. Extended from R:SS to IJRR.
09
Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation
RA-L 2021
Niklas Funk, Charles Schaff, Rishabh Madan, Takuma Yoneda, Julen Urain, Joe Watson, Ethan Gordon, Felix Widmaier, Stefan Bauer, Siddhartha Srinivasa, et al.
A comprehensive benchmark for structured policies and policy optimization methods applied to real-world dexterous object manipulation tasks.
10
ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows
IROS 2020
Julen Urain, Michele Ginesi, Davide Tateo, Jan Peters
Uses normalizing flows to learn deep stable stochastic dynamical systems for imitation learning, combining the expressiveness of deep generative models with stability guarantees.
julen@research:~$