Researcher, Shenzhen Institute of Artificial Intelligence and Robotics for Society
2 papers at NeurIPS 2025
We propose EfficientNav, enabling on-device memory-augmented object-goal navigation system for zero-shot in-door navigation.
The paper presents AnyMDP, a framework for procedurally generating diverse tasks to enhance In-Context Reinforcement Learning (ICRL) scalability, and explores the trade-off between generalization and adaptation efficiency.
