Education

Technische Universit ̈at Wien (TUWien)
Ph. D in Computer Science, advised by Dongheui Lee. Part of PERSEO project: ETN on PErsonalized Robotics as SErvice Oriented applications Supported by Marie Skłodowska-Curie grant.
Spring 2022 - Current
Technische Universit ̈at M ̈unchen (TUM)
Ph. D in Computer Science, advised by Dongheui Lee. Part of PERSEO project: ETN on PErsonalized Robotics as SErvice Oriented applications Supported by Marie Skłodowska-Curie grant.
Fall 2021 - Spring 2022
Universitat Politecnica de Catalunya (UPC)
B.S and M.SC in Telecommunications engineering, with specialization in deep learning.
Fall 2016 - Spring 2021

Employment

CARNET
Research Intern on the development of initial proposals for Project RideSafeUM. Also worked on the development of computer vision applications for Project AntiTrash.
Feb 2020 - May 2021
Seattle, WA
CSIC - Mediterranean Institute for Advanced Studies (IMEDEA)
Researcher on the development of deep neural networks to count, detect and segment fishes through computer vision.
Sep 2020 - Jan 2021
Mallorca, Spain

Publications

Know your limits! Optimize the behavior of bipedal robots through self-awareness
E. Valls Mascaro, D. Lee
Enhance robot behavior to follow any textual and movement command by recognizing its own limitations and expertise
Humanoids 2024 and HFR 2024
I-CTRL: Imitation to Control Humanoid Robots Through Constrained Reinforcement Learning
Y. Yan, E. Valls Mascaro, T. Egle, D. Lee
Control any bipedal humanoid robot by imitating human movements. Any motion, any robot, and in physics-based simulators!
under submission
Robot Interaction Behavior Generation based on Social Motion Forecasting for Human-Robot Interaction
E. Valls Mascaro, Y. Yan, D. Lee
Generating robot motions in social interactions conditioned on semantics, and without any robot data!
ICRA 2024
A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesis
E. Valls Mascaro, H. Ahn, D. Lee
How can we tackle all variations of human motion synthesis using a unique architecture? UNIMASK-M
AAAI 2024
Unsupervised human-to-robot motion retargeting via expressive latent space
Y. Yan, E. Valls Mascaro, D. Lee
Learn how real robots can imitate human movements from different modalities in an unsupervised manner
Humanoids 2023
HOI4ABOT: Human-Object Interaction Anticipation for Assistive roBOTs
E. Valls Mascaro, D. Sliwowski, D. Lee
Detect and anticipate human-object interactions for intention reading, which facilitate robots to assist humans.
CoRL 2023
Human–object interaction prediction in videos through gaze following
Z. Ni, E. Valls Mascaro, H. Ahn, D. Lee
Leveraging gaze provides essential cues for predicting the human intention, which helps to anticipate the human-object interactions.
CVIU, 2023
Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?
H. Ahn, E. Valls Mascaro, D. Lee
Diffusion models offer the right balance between likelihood and diversity when synthesizing human motions from past observations.
ICRA, 2023
Intention-Conditioned Long-Term Human Egocentric Action Forecasting
E. Valls Mascaro, H. Ahn, D. Lee
Understanding the human intention is key for a better prediction of what a human will do in the long-term.
WACV, 2023
Robust Human Motion Forecasting using Transformer-based Model
E. Valls Mascaro, M. Shuo, H. Ahn, D. Lee
Decoupling space and time in human motion forecasting allows for more robust and efficient models.
IROS, 2022