Jue Chen

Shanghai University of Engineering Science, Peking University

Papers

Total Citations

H-Index

About

Jue Chen is a rising researcher at the intersection of computer vision, reinforcement learning, and neuromorphic computing. Her work spans two primary domains: 6D pose estimation and robust deep reinforcement learning. In her highly cited paper "EFN6D: an efficient RGB-D fusion network for 6D pose estimation" (2022, 9 citations), Chen introduced a novel architecture that effectively integrates RGB and depth data, achieving state-of-the-art accuracy in object pose estimation—a critical capability for robotics and augmented reality applications. More recently, Chen has pioneered innovative approaches to reinforcement learning. Her work "Reward guidance for reinforcement learning tasks based on large language models: The LMGT framework" (2025, 5 citations) leverages LLMs to shape reward functions, addressing the sparse reward problem in complex tasks. Additionally, in "BrainQN: Enhancing the Robustness of Deep Reinforcement Learning with Spiking Neural Networks" (2024, 2 citations), Chen explores biologically inspired SNNs as a third-generation network paradigm, demonstrating how their inherent robustness and energy efficiency can overcome the fragility and high power consumption of traditional DRL systems. Through these contributions, Chen is establishing herself as a versatile researcher pushing boundaries in both perception and learning.