Peilin Cai’s Personal Website

About

I am in my third semester of the M.S. in Computer Science program at the University of Southern California. I am a researcher focused on computer vision (CV), large language models (LLMs), and multimodal generation. At USC’s Graphics & Vision Lab (advisor: Prof. Yue Wang), my work centers on 3D reconstruction under sparse observations, controllable generative rendering, and embodied navigation. More broadly, I explore the intersection of generative models, world modeling, and embodied intelligence: how to build interactive, explorable, high-fidelity worlds from very small sets of real images; how to couple geometric priors with diffusion/autoregressive models to produce videos with temporal consistency and realism; and how to make these capabilities run reliably on edge and in-vehicle platforms.

I am also keenly interested in LLM reasoning and multimodal out-of-distribution (OOD) detection. If you are interested in collaborating, please feel free to reach out. My preferred email is peilinca@usc.edu

Publications

CV

Education

• M.S. in University of Southern California, 2024-2026
• B.S. in Wuhan Univeristy, 2020-2024

Work experience

• 2024.11-2025.05: Research Assistant
  • Fortis Lab, USC
  • Supervisor: Yue Zhao, Assistant Professor of USC
  • Research: Multimodal OOD Detection, Large Language Model’s ability on personalization
• 2025.05-Now: Research Assistant
  • GVL Lab, USC
  • Supervisor: Yue Wang, Assistant Professor of USC
  • Research: Computer Vision, 3D Reconstruction and Video Generation for Embodied Navigation

Skills

• Python, C, C++

Publications

• Secure On-Device Video OOD Detection Without Backpropagation

  @article{li2025secure, title={Secure on-device video ood detection without backpropagation}, author={Li, Shawn and Cai, Peilin and Zhou, Yuxiao and Ni, Zhiyu and Liang, Renjie and Qin, You and Nian, Yi and Tu, Zhengzhong and Hu, Xiyang and Zhao, Yue}, journal={arXiv preprint arXiv:2503.06166}, year={2025} }

• A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations

  @article{li2025personalized, title={A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations}, author={Li, Li and Cai, Peilin and Rossi, Ryan A and Dernoncourt, Franck and Kveton, Branislav and Wu, Junda and Yu, Tong and Song, Linxin and Yang, Tiankai and Qin, Yuehan and others}, journal={arXiv preprint arXiv:2505.14106}, year={2025} }