Weixiang (Sweson) Sun

247B Fitzpatrick Hall

Notre Dame, IN 46556

Hi! I’m Weixiang Sun, a first-year Ph.D. student in Computer Science and Engineering at the University of Notre Dame , where I am advised by Yanfang (Fanny) Ye in the Yes-Lab. I received my B.S. in Mathematics from Northeastern University in 2025. At the end of my freshman year, I was selected for an exchange program with the Department of Mathematics at NCSU. During this period, I conducted research in optimization and published my first paper, which sparked my lasting interest in pursuing AI research. I later conducted a research internship at Lehigh University under the supervision of Lichao Sun, with whom I continue to collaborate closely.

My research interests lie in Large Foundation Models and Agentic AI—both in their core aspects (e.g., efficiency, reinforcement learning) and downstream applications in fields such as medicine and finance. Currently, I am focusing on exploring the potential of large language models in psychology, while also investigating the applications of generative models for vision (image, video, and 4D generation).

If you’re interested in my work or would like to collaborate, feel free to reach out at wsun4[at]nd[dot]edu.

news

Aug 16, 2025	Excited to start my Ph.D. at University of Notre Dame.

selected publications

Mora: Enabling generalist video generation via a multi-agent framework

Zhengqing Yuan^*, Yixin Liu^*, Weixiang Sun^*, and 8 more authors

arXiv preprint arXiv:2403.13248, 2024

Abs Code

Text-to-video generation has made significant strides, but replicating the capabilities of advanced systems like OpenAI’s Sora remains challenging due to their closed-source nature. Existing open-source methods struggle to achieve comparable performance, often hindered by ineffective agent collaboration and inadequate training data quality. In this paper, we introduce Mora, a novel multi-agent framework that leverages existing open-source modules to replicate Sora’s functionalities. We address these fundamental limitations by proposing three key techniques: (1) multi-agent fine-tuning with a self-modulation factor to enhance inter-agent coordination, (2) a data-free training strategy that uses large models to synthesize training data, and (3) a human-in-the-loop mechanism combined with multimodal large language models for data filtering to ensure high-quality training datasets. Our comprehensive experiments on six video generation tasks demonstrate that Mora achieves performance comparable to Sora on VBench, outperforming existing open-source methods across various tasks. Specifically, in the text-to-video generation task, Mora achieved a Video Quality score of 0.800, surpassing Sora’s 0.797 and outperforming all other baseline models across six key metrics. Additionally, in the image-to-video generation task, Mora achieved a perfect Dynamic Degree score of 1.00, demonstrating exceptional capability in enhancing motion realism and achieving higher Imaging Quality than Sora. These results highlight the potential of collaborative multi-agent systems and human-in-the-loop mechanisms in advancing text-to-video generation. More visualization results of our work are available at https://mora-2025.github.io/.
EfficientLLM: Efficiency in Large Language Models

Zhengqing Yuan^*, Weixiang Sun^*, Yixin Liu^*, and 8 more authors

arXiv preprint arXiv:2505.13840, 2025

Code Website
Bora: Biomedical generalist video generation model

Weixiang Sun^*, Xiaocao You^*, Ruizhe Zheng^*, and 5 more authors

arXiv preprint arXiv:2407.08944, 2024