Sarath Chandar
Papers
1
Total Citations
3
H-Index
1
About
Sarath Chandar is a leading researcher in artificial intelligence, with a focus on self-supervised learning, video understanding, and world models. His work addresses a fundamental challenge in AI: enabling machines to learn from observation rather than requiring massive amounts of labeled data. Chandar’s most notable contribution is the development of V-JEPA 2, a self-supervised video model that learns to understand, predict, and plan by combining internet-scale video data with minimal interaction data from robot trajectories. This approach represents a significant step toward building AI systems that can generalize across tasks with limited supervision. While his research is still emerging, with his most-cited paper accumulating 3 citations in 2025, the conceptual impact of V-JEPA 2 is already recognized as a pioneering effort in bridging passive observation and active learning. Chandar’s work is particularly relevant for students and researchers interested in unsupervised representation learning, embodied AI, and the intersection of computer vision and robotics. His contributions promise to shape how future AI systems learn from the world around them.
Research Focus
Key Achievements
Top Papers
- 1