Tejas Kulkarni
Papers
1
Total Citations
6
H-Index
1
About
Tejas Kulkarni is a leading researcher at the intersection of artificial intelligence, robotics, and representation learning. His work fundamentally addresses how machines can build structured, reusable models of the world to enable more efficient and intelligent behavior. Kulkarni’s most influential contributions center on the idea that *representation matters*—that projecting high-dimensional sensory data into lower-dimensional, structured representations can dramatically improve data efficiency in reinforcement learning, particularly for robotics where data is scarce. His seminal paper, “Representation Matters: Improving Perception and Exploration for Robotics” (2021), with 6 citations, poses a critical question: can a single, generally useful representation be found that works across tasks and domains? This work has helped shift the field toward learning reusable abstractions rather than task-specific features. Kulkarni’s research is notable for bridging deep learning, cognitive science, and robotics, and he is recognized for advancing the principles of compositional and disentangled representations. His vision continues to inspire new approaches to building agents that learn faster, explore more intelligently, and generalize across environments.
Research Focus
Key Achievements
Top Papers
- 1