Binghang Lu

Binghang Lu

Graduate Researcher, Purdue ECE — LLMs · Continual Learning · AI4S

Publications

You can also find my articles on my Google Scholar profile.

Large Language Models & Safety

Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering

Published in arXiv preprint, 2026

Characterizes how chain-of-thought reasoning compounds safety failures in large reasoning models and proposes adaptive multi-principle steering as a mitigation.

Recommended citation: Li, X., Hou, J., Deng, Z., Zhang, Z., Li, T., Lu, B., Hu, B., Zhao, Y., & Hao, Y. (2026). "Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering." arXiv:2605.05678.
Download Paper

LLM Continual Learning

Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning

Published in arXiv preprint, 2026

A spectral orthogonal-gradient-projection variant of the Muon optimizer that enables LLMs to acquire new tasks while preserving prior capabilities.

Recommended citation: Lu, B., Deng, Z., Zhang, R., Hu, B., Zhao, Y., Tian, Y., Mou, C., Lin, G., & Li, X. (2026). "Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning." arXiv:2605.08949.
Download Paper

AI for Science (AI4S)

Morphy-Net: Evolutionary Multi-Objective Optimization for Replica-Exchange-Based Physics-Informed Neural Operator Learning Networks

Published in Computer Methods in Applied Mechanics and Engineering (CMAME), 2026

Evolutionary multi-objective optimization combined with replica exchange for training physics-informed neural operator networks. Accepted by CMAME 2026.

Recommended citation: Lu, B., Mou, C., & Lin, G. (2026). "Morphy-Net: Evolutionary Multi-Objective Optimization for Replica-Exchange-Based Physics-Informed Neural Operator Learning Networks." Computer Methods in Applied Mechanics and Engineering (accepted).
Download Paper

Neural-POD: A Plug-and-Play Neural Operator Framework for Infinite-Dimensional Functional Nonlinear Proper Orthogonal Decomposition

Published in arXiv preprint, 2026

A plug-and-play neural operator framework for infinite-dimensional functional nonlinear POD, enabling efficient reduced-order modeling of complex PDE systems.

Recommended citation: Mou, C., Lu, B., & Lin, G. (2026). "Neural-POD: A Plug-and-Play Neural Operator Framework for Infinite-Dimensional Functional Nonlinear Proper Orthogonal Decomposition." arXiv:2602.15632.
Download Paper

MoPINNEnKF / iPINNER: Iterative Physics-Informed Neural Network with Ensemble Kalman Filter

Published in Journal of Computational Physics, 2025

An iterative PINN–EnKF framework that couples physics-informed networks with ensemble Kalman filtering for robust parameter and state estimation under uncertainty.

Recommended citation: Lu, B., Mou, C., & Lin, G. (2025). "iPINNER: An iterative physics-informed neural network with ensemble Kalman filter." Journal of Computational Physics, 114592.
Download Paper

fPINN-DeepONet: A Physics-Informed Operator Learning Framework for Multi-Term Time-Fractional Mixed Diffusion–Wave Equations

Published in Journal of Computational Physics, 2025

A physics-informed DeepONet that learns the solution operator of multi-term time-fractional mixed diffusion–wave equations.

Recommended citation: Lu, B., Hao, Z.-P., Moya, C., & Lin, G. (2025). "fPINN-DeepONet: A physics-informed operator learning framework for multi-term time-fractional mixed diffusion–wave equations." Journal of Computational Physics, 538, 114184.
Download Paper

Research on the Use of YOLOv5 Object Detection Algorithm in Mask Wearing Recognition

Published in World Scientific Research Journal, 2020

A YOLOv5-based real-time object detection system for recognizing mask-wearing behavior during the COVID-19 pandemic.

Recommended citation: Liu, Y., Lu, B. H., Peng, J., & Zhang, Z. (2020). "Research on the use of YOLOv5 object detection algorithm in mask wearing recognition." World Scientific Research Journal, 6(11), 276–284.