Marc Szafraniec

Papers

1

Total Citations

3

H-Index

1

About

Marc Szafraniec is a leading researcher in self-supervised learning and video understanding, with a focus on building AI systems that learn from observation. His most notable contribution is the development of V-JEPA 2 (2025), a groundbreaking framework that combines internet-scale video data with minimal robot interaction data to create models capable of understanding, predicting, and planning in the physical world. This work addresses a fundamental challenge in modern AI: enabling machines to learn world models largely through passive observation, akin to how humans learn. Szafraniec’s research bridges the gap between self-supervised video representation learning and embodied AI, demonstrating that models can acquire rich spatiotemporal understanding without extensive labeled data or large-scale robotic interaction. His approach has significant implications for robotics, autonomous systems, and general-purpose AI, offering a scalable path toward agents that can reason about and act in complex environments. With his work already garnering attention in the AI community, Szafraniec continues to push the boundaries of how machines perceive and interact with the world through self-supervised learning.

Research Focus

Key Achievements

1
H-Index
1
Papers
3
Total Citations
3
Avg Citations/Paper
🏆 Most Cited Paper
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
3 citations · 2025
📈 Most Prolific Year: 2025 (1 Papers)
🤝 Key Collaborators: 28

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago