Nikolaos Sotirakis
Papers
1
Total Citations
1
H-Index
1
About
Nikolaos Sotirakis is a rising researcher at the intersection of reinforcement learning, robotics, and language-guided AI. His work focuses on enabling robots to learn and generalize across multiple tasks, moving beyond the limitations of single-task agents. His most notable contribution, "LIMT: Language-Informed Multi-Task Visual World Models" (2025), introduces a framework that leverages natural language to inform and unify multi-task visual world models, significantly improving sample efficiency and generalization in robotic learning. This work addresses a critical bottleneck in real-world robotics—the need for versatile, adaptable agents. Though early in its trajectory, Sotirakis’s research is already gaining traction, with his work cited by peers exploring scalable, language-conditioned robot learning. By bridging language and multi-task reinforcement learning, he is helping to shape a future where robots can understand and execute diverse instructions with minimal retraining, a key step toward truly autonomous and helpful embodied AI.
Research Focus
Key Achievements
Top Papers
- 1LIMT: Language-Informed Multi-Task Visual World Models1 citations · 2025