Haoyu Wang

This researcher works on machine learning topics including federated learning, machine unlearning (methods for removing data influence from trained models), knowledge editing in large language models, and multimodal learning that combines signals like text, images, and sensor data (e.g., mmWave and acoustic signals). Recent work also touches on privacy-preserving optimization techniques such as noisy gradient descent, as well as applied projects like object detection using drone imagery. This profile suggests a focus on making machine learning models more efficient, adaptable, and privacy-conscious.

Publication output was minimal or absent from 2017 to 2022 but grew sharply starting in 2023, with a notably high and steady output in 2024 and 2025.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026