Ziqin Yuan

Purdue University West Lafayette

Papers

4

Total Citations

18

H-Index

3

About

Ziqin Yuan is at the forefront of human-robot interaction (HRI) and multi-agent systems, pioneering methods to make robots more adaptive and responsive to human needs. His research centers on two key challenges: personalizing robot behavior through human feedback and optimizing task allocation in complex, mixed teams. Yuan’s major contribution is the development of **PrefCLM**, a framework that leverages crowdsourced large language models to dramatically reduce the human feedback required for preference-based reinforcement learning (PbRL), addressing a critical bottleneck in the field (9 citations). He further advances personalization in HRI by introducing preference-based action representation learning, enabling robots to adapt to individual users without retraining from scratch. On the team coordination front, Yuan tackles the intricate problem of task allocation in multi-human multi-robot (MHMR) teams, accounting for team heterogeneity, dynamic execution, and information uncertainty—a challenge few have addressed holistically. With over 18 citations across his recent works, all published in 2024-2025, Yuan is rapidly establishing himself as a rising star whose work promises to make collaborative robotics more intuitive, efficient, and truly human-centric.

Research Focus

Key Achievements

3
H-Index
4
Papers
18
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
PrefCLM: Enhancing Preference-Based Reinforcement Learning With Crowdsourced Large Language Models
9 citations · 2025
📈 Most Prolific Year: 2025 (3 Papers)
🤝 Key Collaborators: 10
🏛 Institutions: Purdue University West Lafayette

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago