YIMIN TANG
Scholar

YIMIN TANG

Google Scholar ID: OrBSEjAAAAAJ
University of Southern California
RoboticsReinforcement LearningMulti Agent Path Finding
Citations & Impact
All-time
Citations
65
 
H-index
3
 
i10-index
2
 
Publications
10
 
Co-authors
13
list available
Publications
10 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks (IROS 2025, ICRA 2025 Workshop on Foundation Models and Neuro-Symbolic AI for Robotics, SoCS 2025 extended abstract)
  • Accelerating Focal Search in Multi-Agent Path Finding with Tighter Lower Bounds (IROS 2025, RSS 2025 Workshop on Scalable and Resilient Multi-Robot Systems)
  • Enhancing Lifelong Multi-Agent Path Finding with Cache Mechanism (AAMAS 2025 Workshop on Autonomous Robots and Multirobot Systems, in review)
  • Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism (NeurIPS 2024 Workshop on Adaptive Foundation Models)
  • ITA-ECBS: A Bounded-Suboptimal Algorithm for Combined Target-Assignment and Path-Finding Problem (SoCS 2024)
  • Solving Multi-Agent Target Assignment and Path Finding with a Single CBS Tree (IEEE MRS 2023, Best Paper Candidate)
  • Multi-modal perception and transfer learning for grasping transparent and specular objects (RA-L with ICRA 2020)
Background
  • Research Interests: Multi-Agent Path Finding (MAPF), foundation model, world model. Professional field: Computer Science.
Miscellany
  • Familiar with traditional data structures and algorithms, several prizes in National Olympiad in Informatics in Provinces (NOIP), National Olympiad in Informatics (NOI), and International Collegiate Programming Contest (ICPC). First programming language is Pascal.