Wanqi Yang
I am a PhD student at the ELLIS Institute Tübingen and the Max Planck Institute for Intelligent Systems, supervised by Dr. Shiwei Liu.
I focus on AI models, systems, hardware, and the productization trends that connect them. My long-term vision is to help build a more individually sovereign digital future by making machine learning systems more efficient, stable, and accessible.
I try to work toward this goal in three ways: as a researcher, by pushing forward questions in efficient machine learning systems; as a developer, by building tools and systems in this space; and as a writer, by using my personal blog to share knowledge, experience, and practical intuition about efficient ML systems and the latest AI tools.
As a researcher
I focus on how to build efficient and scalable machine learning systems. At the same time, I am exploring how to apply knowledge and experience from this field to Recursive Self Improvement (RSI) for machine learning systems.
Before starting my PhD, I worked with Dr. Shiwei Liu and Dr. Yuexiao Ma on empirical studies for improving the efficiency of foundation models. One result from this line of work is AlphaQ, a calibration-free bit-allocation method for Mixture-of-Experts quantization. I also completed my master's thesis in the Hardware for Artificial Intelligence Lab at TU Darmstadt, where I studied classification-difficulty-aware neural network quantization. I also worked as a research assistant in the Artificial Intelligence & Machine Learning Lab at TU Darmstadt, building a cloud-based experimental environment for studying learning-agent behavior through multi-agent interactions. My undergraduate thesis was completed in the robotics lab at Beijing Jiaotong University, where I carried out the full design process for a multi-form robot and received an Outstanding Undergraduate Thesis award.
As a developer
In my engineering work, I care about the moment when a model has to leave a clean experimental setting and become a system that actually runs. At Qualcomm, I worked on multimodal model inference for mobile and PC platforms, where model design, runtime behavior, and hardware constraints have to be considered together.
Earlier at DJI, I worked on heterogeneous inference for autonomous-driving perception models. That experience made the deployment side of machine learning very concrete to me, and it still keeps pulling me toward a whole-stack view: representations and learning algorithms on one side, deployment pipelines and low-level backends on the other.
Outside work, I also like building small tools that make a workflow more inspectable or reduce the friction between an idea and a runnable system. Recently, I have been especially interested in local AI products in the macOS ecosystem. Some of these experiments are collected on my Project page.
As a writer
I write in Chinese under the name Vinci叽里呱啦. I treat it as a habit of learning and self-expression. I mainly record how I understand complex concepts that interest me, along with my own practical experience. I publish on Zhihu, WeChat Official Account, and X; you are warmly welcome to follow along.
How I got here
My path into this area has been driven by curiosity. As an undergraduate at Beijing Jiaotong University, I used my laptop for computation and simulation work related to robotics and racing-car aerodynamics. That experience made the value of computing power very concrete to me: faster and more accessible computation changes how quickly we can iterate, test, and explore in science and engineering. It also led me to pursue a master's degree in Computational Engineering at TU Darmstadt.
Outside work
- I read, play tennis, hike, take photographs, and read tarot.
- I once won the Encyclopedic Knowledge Competition at Beijing Jiaotong University.
- In my sophomore year, I built a Formula Student race car with close friends, and our team achieved its best result at the time.
- At TU Darmstadt, I started the Chinese tennis community from scratch and organized regular events.