Quentin Garrido
Papers
1
Total Citations
3
H-Index
1
About
Quentin Garrido is an AI researcher specializing in self-supervised learning and video understanding, with a particular focus on developing models that can learn rich representations of the world without requiring extensive labeled data. His most notable work, **V-JEPA 2** (2025), represents a significant step forward in the field of world modeling — exploring how AI systems can learn to understand, predict, and plan by observing internet-scale video data combined with a small amount of robotic interaction data. This research tackles one of the core challenges in modern artificial intelligence: enabling models to develop a grounded understanding of physical reality largely through passive observation, with implications spanning video understanding, robotics, and embodied AI. Though V-JEPA 2 is early in its citation trajectory with 3 citations at time of writing, its ambitions place it at the frontier of joint perception and planning research, an area attracting enormous interest from both academia and industry. Garrido's work sits at the intersection of representation learning, video foundation models, and autonomous agents — making him a researcher to watch as the field of self-supervised world models continues to rapidly evolve and mature.
Research Focus
Key Achievements
Top Papers
- 1