Xiaofeng Mou

Papers

Total Citations

H-Index

About

Xiaofeng Mou is a rising researcher at the forefront of embodied AI, with a focus on enabling intelligent agents to operate effectively in complex, real-world environments. Their most-cited work, "Retrieval-Augmented Embodied Agents" (2024), addresses a critical bottleneck in robotics and AI: the heavy reliance on vast training datasets. Mou’s key contribution is a novel framework that equips embodied agents with retrieval-augmented capabilities, allowing them to leverage external knowledge and past experiences on the fly—much like human recall—rather than memorizing every scenario. This approach significantly reduces the need for exhaustive training data while enhancing adaptability and decision-making in uncertain settings. With 9 citations in just its first year, this paper signals strong early impact and growing recognition in the community. Mou’s work bridges the gap between large-scale pretraining and practical, data-efficient deployment, making it especially relevant for students and researchers interested in robotics, reinforcement learning, and human-inspired AI systems. Their research promises to accelerate the development of more autonomous, resourceful agents for real-world tasks.