Zeyu Yan
Papers
2
Total Citations
3
H-Index
1
About
Zeyu Yan is a robotics researcher whose work bridges the gap between human-like decision-making and autonomous manipulation systems. His primary research areas include robotic manipulation, meta-learning, and domain adaptation, with a focus on enabling robots to learn from past experiences and adapt to novel environments. Yan’s most cited paper, “Integrating Historical Learning and Multi-View Attention with Hierarchical Feature Fusion for Robotic Manipulation” (2024, 2 citations), addresses a critical limitation in robotics: the tendency of action prediction models to rely solely on current observations, ignoring environmental changes. By incorporating historical learning and multi-view attention, his work enhances robotic adaptability and robustness. His second notable contribution, “Learning from Demonstrations via Deformable Residual Multi-Attention Domain-Adaptive Meta-Learning” (2025, 1 citation), tackles the challenge of rapid robot adaptation to unseen environments through meta-learning inspired by biological processes. Though early in his career, Yan’s innovative integration of attention mechanisms and hierarchical feature fusion is laying the groundwork for more intelligent, context-aware robotic systems. His research holds promise for applications in manufacturing, healthcare, and service robotics, where adaptive manipulation is essential.
Research Focus
Key Achievements
Top Papers
- 1
- 2