Mojtaba
Papers
1
Total Citations
3
H-Index
1
About
Mojtaba is a leading researcher in self-supervised learning and video understanding, with a focus on building AI systems that learn from observation rather than massive labeled datasets. His most-cited work, "V-JEPA 2" (2025), tackles a fundamental challenge in modern AI: enabling models to comprehend the world and plan actions through internet-scale video data, supplemented by minimal interaction data from robot trajectories. This approach bridges the gap between passive observation and active decision-making, advancing the frontiers of video prediction and robotic planning. With 3 citations already in its first year, the paper signals growing interest in his paradigm of learning world models without explicit supervision. Mojtaba’s contributions are particularly notable for their potential to reduce the data and annotation burden in robotics and embodied AI, making learning more scalable and efficient. His work stands at the intersection of computer vision, self-supervised learning, and robotics, offering a promising path toward generalist agents that can understand and act in dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1