Changming Wu
Papers
2
Total Citations
544
H-Index
2
About
Changming Wu is a pioneering researcher at the intersection of materials science, machine learning, and advanced optoelectronics. Their work centers on two transformative areas: accelerating materials discovery through autonomous experimentation and developing next-generation intelligent image sensors. Wu’s most impactful contribution is the development of “on-the-fly closed-loop materials discovery via Bayesian active learning,” a seminal work with 325 citations that demonstrates how active learning—a machine learning paradigm for optimal experiment design—can autonomously guide scientific discovery, reducing the time and cost of identifying novel materials. This approach, with roots tracing back to Laplace, represents a paradigm shift toward self-driving laboratories. In parallel, Wu has made significant strides in in-sensor computing with their 2022 paper on “programmable black phosphorus image sensors for broadband optoelectronic edge computing” (219 citations). By leveraging two-dimensional semiconductors like black phosphorus, Wu created image sensors capable of performing computational tasks internally—such as edge detection—directly on the sensor plane. This innovation dramatically reduces latency and power consumption for machine vision in robotics and distributed systems, paving the way for more efficient, brain-inspired visual processing. Wu’s work is not only highly cited but also foundational for the future of autonomous science and intelligent hardware.
Research Focus
Key Achievements
Top Papers
- 1
- 2