Wenqi Liang

Papers

Total Citations

H-Index

About

Wenqi Liang is a researcher at the forefront of 3D computer vision, with a primary focus on incremental learning for 3D object detection—a critical challenge for real-world systems like autonomous driving, robotics, and augmented reality. Their most notable contribution, the I3DOD framework (2023), directly tackles the problem of catastrophic forgetting in class-incremental scenarios, where traditional detection models lose the ability to recognize previously learned objects when trained on new classes. By introducing a novel prompting mechanism, Liang’s work enables models to adapt continuously without retraining from scratch, a breakthrough for dynamic environments. Although early in its citation impact (2 citations), I3DOD represents a forward-looking solution to a pressing issue in lifelong machine learning. Liang’s research bridges the gap between static, high-performance detection and the need for scalable, memory-efficient systems that learn over time. Their work is particularly relevant for students and engineers developing autonomous agents that must operate safely and robustly in changing, open-world settings.