Runqian (Ray) Wang

I am an undergraduate student at Massachusetts Institute of Technology double majoring in Artificial Intelligence and Mathematics . My current research interest is in generative modeling.

I am currently working with Professor Kaiming He at MIT and Professor Yilun Du at Harvard University. Previously, I was fortunate to have collaborated with Professor Aude Oliva (MIT), Professor Polina Golland (MIT), Dr. Zhirong Wu (Microsoft), and Dr. Rogerio Feris (IBM).

Email / CV / Github

Research

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

	Diffuse and Disperse: Image Generation with Representation Regularization Runqian Wang, Kaiming He Paper Plug-and-play representation regularizer for generative modeling that brings consistent improvement across different settings.
	Trans-LoRA: towards data-free Transferable Parameter Efficient Finetuning Runqian Wang, Soumya Ghosh, David Cox, Diego Antognini, Aude Oliva, Rogerio Feris, Leonid Karlinsky Advances in Neural Information Processing Systems, 37, 2024 Paper 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.
	Feature Selection for Malapposition Detection in Intravascular Ultrasound-A Comparative Study Satyananda Kashyap, Neerav Karani, Alexander Shang, Niharika D’Souza, Neel Dey, Lay Jain, Ray Wang, Hatice Akakin, Qian Li, Wenguang Li, Corydon Carlson, Polina Golland, Tanveer Syeda-Mahmood Second International Workshop, AMAI, 2023 Paper 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.
	An efficient algorithm to compute the X-ray transform Chong Chen, Runqian Wang, Chandrajit Bajaj, Ozan Öktem Intl Journal of Computer Mathematics, 2022 Paper Proposes a new algorithm to compute the X-ray transform of an image; improves time complexity from O(N^d) to O(N).
	Comparing Grover’s Quantum Search Algorithm with Classical Algorithm on Solving Satisfiability Problem Runqian Wang, IEEE Integrated STEM Education Conference , 2021 Paper Applies Grover's quantum search algorithm to solve satisfiability problems and reduces time complexity to the square root of existing solutions.
	Incorporating Frame Image and Frame Sequence into Ensemble Learning Networks to Improve the Accuracy of Physical Bullying-Detecting Model Runqian Wang IOP Conference Series, 2019 Paper Proposes an ensemble learning neural network for violence detection in videos; achieves over 90% accuracy with speed of 75 FPS.