Lening Wang

University of Houston

Papers

1

Total Citations

7

H-Index

1

About

Lening Wang is a researcher at the forefront of efficient and reliable deep learning, with a primary focus on Bayesian Neural Networks (BNNs) and their deployment in safety-critical AI systems. His work addresses the fundamental challenge of making BNNs—which provide crucial uncertainty estimates for robust decision-making—practical for real-world applications. Wang’s most notable contribution, the "Shift-BNN" framework (2021, 7 citations), introduces a highly-efficient probabilistic training method that leverages memory-friendly pattern retrieval. This innovation significantly reduces the computational and memory overhead typically associated with Bayesian inference, enabling BNNs to be trained on resource-constrained devices without sacrificing the uncertainty quantification vital for domains like autonomous driving, medical image diagnosis, and rescue robotics. By bridging the gap between theoretical robustness and practical efficiency, Wang’s research is paving the way for safer, more trustworthy AI deployments in high-stakes environments. His work stands as a key reference for researchers and engineers seeking to integrate principled uncertainty estimation into next-generation intelligent systems.

Research Focus

Key Achievements

1
H-Index
1
Papers
7
Total Citations
7
Avg Citations/Paper
🏆 Most Cited Paper
Shift-BNN: Highly-Efficient Probabilistic Bayesian Neural Network Training via Memory-Friendly Pattern Retrieving
7 citations · 2021
📈 Most Prolific Year: 2021 (1 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: University of Houston

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago