Abhinav Shrivastava

Papers

Total Citations

H-Index

About

Abhinav Shrivastava is a leading researcher at the forefront of open-world learning and robotics, pushing the boundaries of how machines adapt to novel, unstructured environments. His most-cited work, "Challenges, evaluation and opportunities for open-world learning" (2024, 25 citations), serves as a foundational roadmap for the field, systematically defining the core obstacles and future directions for AI systems that must operate beyond closed, static datasets. This contribution has quickly become a key reference for researchers tackling lifelong learning and distribution shift. In robotics, Shrivastava’s innovative "WayEx: Waypoint Exploration using a Single Demonstration" (2024) introduces a paradigm-shifting approach to imitation learning, enabling complex goal-conditioned tasks to be learned from just one expert example—without requiring action information. This breakthrough dramatically reduces the data burden for robot training, opening new possibilities for few-shot skill acquisition. By bridging theoretical frameworks with practical, data-efficient algorithms, Shrivastava is shaping the next generation of adaptive, autonomous systems. His work is essential reading for anyone interested in how machines can learn, explore, and generalize in the real world.