Lorenzo Mur-Labadia
Lorenzo Mur-Labadia
Embedded Files
I completed my PhD on Deep Learning and Computer Vision at the University of Zaragoza (Spain), supervised by Prof. Rubén Martínez-Cantín and Prof. Josechu Guerrero.
My research focuses on video understanding, video–language learning, and 4D scene representations; with applications to embodied and egocentric perception.
During my PhD, I developed visual models for segmentation, detection, forecasting, and representation learning, leading to 8 first-author publications at top-tier computer vision venues, including ICRA 2023, ICCV 2023, IROS 2023, ECCV 2024, CVPR 2025, ICCV 2025 and 2 journals (CVIU and T-PAMI).
From June to November 2025, I was a Research Scientist intern at Meta AI (FAIR) in Paris, where I work with Adrien Bardes, Nicolas Ballas and Yann LeCun on large-scale self-supervised video understanding. The result of my internship was V-JEPA 2.1, the best video representation system in the world.
Now, I am Research Scientist at Multiverse Computing, building quantum-inspired models and Assistant Professor at the University of Zaragoza.
Latest news 🗞️
Latest news 🗞️
[15/03/2026] VJEPA 2.1 is already here!! This is outcome of my internship at META, supervised by A.Bardes, N.Ballas and Y.LeCun
[16/02/2026] T-PAMI Q1 Journal accepted! This is the result of my collaboration with Prof. GM.Farinella and A.Furnari, during my internship at the University of Catania. First, we publish an ECCV 2024 paper, and then we extend it to a T-PAMI journal, which was finally accepted.
[20/01/2026 ] I defend my PhD "Learning visual models for egocentric vision" with Cum Laude.
[11/09/2025] O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views will be introduced at ICCV 2025 in Hawai 🏖️
[10/06/2025] O-MaMa won the EgoVIS Object Correspondences challenge at CVPR 2025!!!
Latest works 📜
Latest works 📜
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
Lorenzo Mur-Labadia , Matthew Muckley, Amir Bar, Mido Assran, Koustuv Sinha, Mike Rabbat, Yann LeCun, Nicolas Ballas, Adrien Bardes
Integrating Affordances and Attention Models for Short-Term Object Interaction
Integrating Affordances and Attention Models for Short-Term Object Interaction
Lorenzo Mur-Labadia*, Josechu Guerrero, Ruben Martinez-Cantin, G.M. Farinella, A.Furnari
Accepted in T-PAMI 2026 (Journal Q1)
Preprint on Arvix
O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views
O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views
Lorenzo Mur-Labadia*, Maria Santos-Villafranca*, Jesus Bermudez-Cameo, Alejandro Perez-Yus, Ruben Martinez-Cantin, Jose J. Guerrero.
Accepted in ICCV 25' https://github.com/Maria-SanVil/O-MaMa
DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos
DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos
Lorenzo Mur-Labadia*, Josechu Guerrero, Ruben Martinez-Cantin
Accepted in CVPR 25'
Preprint on Arvix
AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation
AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation
Lorenzo Mur-Labadia*, Josechu Guerrero, Ruben Martinez-Cantin, Giovanni Maria Farinella and Antonino Furnari
Accepted in ECCV 24'
2nd place at the Ego4D Short Term Anticipation Challenge at CVPR 24' 🥈
Bayesian temporal-order priors for test time refinement
Bayesian temporal-order priors for test time refinement
Carlos Plou, Lorenzo Mur-Labadia*, Ruben Martinez-Cantin and Ana C.Murill
1nd place at the Ego4D Step Grounding Challenge at CVPR 24' 🥇
Paper on Arvix
Multi-label affordance mapping from egocentric vision (ICCV 2023) ✨
Multi-label affordance mapping from egocentric vision (ICCV 2023) ✨
Lorenzo Mur-Labadia*, Josechu Guerrero and Ruben Martinez-Cantin
Resume
Resume
Research Internship at the University of Catania 🇮🇹, supervised by G. Farinella and A. Furnari, working on next-active object anticipation.
PhD Computer Vision and Bayesian Deep Learning, supervised by J. Guerrero and Ruben Martinez-Cantin, University of Zaragoza (2022-Current)
Research Internship at University of Freiburg 🇩🇪(2021-2022), supervised by Abhinav Valada working on Panoptic Scene Completion for my Master Thesis.
MSc Computer Vision, Robotics and Graphics University of Zaragoza (2020-2022), Grade: 8.52 out 10.
BSc Industrial Technologies Engineering. University of Zaragoza (2016-2020) Grade 8.43 out 10. Awarded with the academic excellence award.
Spanish Baccaleurate 9.82/10 points and International Baccaleurate (IB) 42/45 points cursed at the same time (2014-2016)
Teaching 🧑🏫
Teaching 🧑🏫
2024/2025 Machine Learning, MSc Robotics, Graphics and Computer Vision
2023/2024 Automatics systems. BSc Mechanical Engineering
2023/2024 I supervised the Master Thesis of Alejandro de Nova about Feature Fields in Egocentric Video
2022/2023 Industrial Robotics and Automatics. BSc Industrial Technologies Engineering
2022/2023 I supervised the Master Thesis of Miguel Marcos about Music generation with Bayesian optimization
2022/2023 Computer Vision and Robotics. MSc Industrial Technologies Engineering
2022/2023 Master Thesis co-supervision with Ruben Martinez Cantin. MSc Robotics, Graphics and Computer Vision
Other interests 🎭🏕️
Other interests 🎭🏕️
I've been participating as volunteer in a youth association for 8 years. We prepare weakly activities, summer camps and I have supervised the performance of several musicals: High School Musical, Mamma Mia! and Grease. My other interests are hiking at the Pyrenees and I play both viola and guitar. 🎻 🎸
Contact me! lmur@unizar.es
Contact me! lmur@unizar.es
DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos
DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos
Lorenzo Mur-Labadia*, Josechu Guerrero, Ruben Martinez-Cantin
Accepted in CVPR 25'
Preprint on Arvix
Page updated
Report abuse