Vigneshwaran Subbaraju

Institute of High Performance Computing, Agency for Science, Technology and Research

Papers

Total Citations

H-Index

About

Vigneshwaran Subbaraju is a leading researcher at the intersection of human-robot interaction and multi-modal machine learning, with a core focus on enabling more natural, intuitive communication between humans and robotic agents. His work centers on how robots can better understand ambiguous human instructions by integrating multiple input modalities, particularly gestures and gaze. Subbaraju’s major contributions include the development of M2Gestic, a system that leverages naturally-generated pointing gestures to significantly improve comprehension accuracy in collaborative tasks, as demonstrated in his 2020 paper (11 citations). He further advanced the field with COSM2IC (2022, 9 citations), which tackles the critical challenge of optimizing real-time, on-device execution of multi-modal instruction comprehension models for embodied interaction. His 2021 work on gaze-assisted visual grounding (6 citations) expands this paradigm, showing how eye-tracking can further disambiguate human intent. Collectively, Subbaraju’s research—garnering over 25 citations—is pioneering the shift toward more responsive, context-aware robotic systems that can seamlessly interpret the rich, non-verbal cues humans naturally use, laying essential groundwork for the next generation of collaborative robots.