Runqian (Ray) Wang

I am an undergraduate student at Massachusetts Institute of Technology studying Mathematics and Artificial Intelligence and Decision Making. My current research interest is in generative modeling. I am also broadly interested in machine learning topics including representation learning, optimization, and etc.

Related graduate level courses I have taken include machine learning, probability, distributed algorithms, and computer vision. I have also taken natural language processing, linear algebra, algorithms and data structure, and representation, inference and reasoning.

I am open for chat and discussions, so please feel free to reach out!

Email  /  CV  /  Github

I used to work on computer vision (medical imaging, motion detection), optimization, natural language processing (LLM finetuning), and algorithms. My current focus is on generative modeling. I was also a research intern at Microsoft Research and IBM Research, and my work was spotlighted on Microsoft's official social media.

Plug-and-play representation regularizer for generative modeling that brings consistent improvement across different settings.

Enables nearly data-free and compute-efficient transfer of existing PEFT modules trained on old base model to new base models, while at least preserving, in most cases improve, performance.

Provides a comprehensive study on malposition detection using deep learning approaches and proposes a new approach for malposition classification using Mask-RCNN and SWIN transformer.

Proposes a new algorithm to compute the X-ray transform of an image; improves time complexity from O(N^d) to O(N).

Proposes an ensemble learning neural network for violence detection in videos; achieves over 90% accuracy with speed of 75 FPS.

Applies Grover's quantum search algorithm to solve satisfiability problems and reduces time complexity to the square root of existing solutions.