Qinyuan Wu

I am a third-year PhD student at the CS@Max Planck and the Max Planck Institute for Software Systems (MPI-SWS), advised by Krishna Gummadi. I am also fortunate to closely collaborate with and receive guidance from Evimaria Terzi (Boston University), Mariya Toneva (MPI-SWS), and Muhammad Bilal Zafar (Ruhr University Bochum) (Odered by last name alphabet). Before I joined MPI-SWS, I got my bachelor degree in mathematics-physics from University of Electronic Science and Technology of China (UESTC).

My research focuses on understanding the inner workings of deep learning models to build more reliable and transparent AI systems, with an emphasis on Large Language Models (LLMs). Specifically, I investigate how these models encode, retrieve, and process information, delving into questions like memorization, latent knowledge estimation and knowledge injection of LLMs. My goal is to uncover insights that will enable the development of dependable and interpretable deep learning systems.

Beyond this, I am enthusiastic about collaborating on:

1. Privacy and security challenges in LLMs – exploring ways to mitigate risks while maintaining model utility.
2. The intersection of neuroscience and language models – investigating how insights from the human brain can inform AI research and vice versa.
3. Systems for serving LLMs – including Parameter-Efficient Fine-Tuning (PEFT), quantization, and inference optimization methods like KV caching. While not an expert in LLM systems, I find it fascinating to explore how these optimizations influence model behavior.