Sameer Khurana
Papers
1
Total Citations
4
H-Index
1
About
Sameer Khurana’s research lies at the dynamic intersection of robotics, multimodal machine learning, and human-robot interaction. His most notable contribution, “Interactive Robot Action Replanning using Multimodal LLM Trained from Human Demonstration Videos” (2025), pioneers a novel framework that enables robots to interpret and adapt their actions by learning from audio-visual human demonstrations. By leveraging multimodal large language models and audio-visual Transformers, Khurana’s work addresses a critical bottleneck in robotics: the ability to perform complex manipulation tasks and collaborate seamlessly with humans in unstructured environments. This approach allows robots to not only observe but also dynamically replan their actions in real time, moving beyond rigid pre-programmed behaviors. With 4 citations already in its publication year, this work signals growing recognition of its potential to reshape autonomous systems. Khurana’s contributions are particularly impactful for advancing generalist robots capable of understanding nuanced human cues—a key step toward practical, everyday robotic assistants. His research promises to bridge the gap between human demonstration and robotic execution, making him a rising voice in embodied AI and human-centered robotics.
Research Focus
Key Achievements
Top Papers
- 1