Weilin Yuan

National University of Defense Technology

Papers

Total Citations

H-Index

About

Weilin Yuan’s research lies at the intersection of embodied AI, semantic scene understanding, and decision-making, with a focus on enabling intelligent agents to perceive, reason, and act in complex indoor environments. In their work on Vision-and-Language Navigation (VLN), Yuan proposed a novel framework that incorporates external knowledge reasoning and an assistant’s help, moving beyond rigid step-by-step instructions toward more flexible, real-world navigation—a paper that has already garnered 8 citations. To advance scene representation, Yuan introduced the Topological Scene Map (TSM), a semantic map that fuses behavioral topological maps with scene graphs for comprehensive indoor environment understanding, also cited 8 times. More recently, Yuan contributed a comprehensive survey on Transformers in reinforcement learning for decision-making, covering applications from autonomous driving to robotic manipulation and gaming AI. This work highlights Yuan’s role in synthesizing cutting-edge advances in transformer architectures for RL, offering a valuable resource for researchers. With a growing citation footprint and a focus on bridging perception, reasoning, and action, Yuan’s work is shaping the future of embodied intelligence and autonomous systems.