Cissy Xie

legally known as 谢林汐 (Linxi Xie)

prof_pic.jpg

Hi! I’m an incoming Ph.D. student at The University of Texas at Austin. Previously, I obtained a B.S. in Computer Science from New York University Shanghai and New York University.

I have been fortunate to work with Prof. Hongyi Wen and Prof. Shengjie Wang on personalization of diffusion models and machine unlearning for mitigating undesirable data influence in LLMs. I was also a Visiting Student Researcher at the Stanford Computational Imaging Lab, advised by Prof. Gordon Wetzstein, where I worked on video world models. Broadly, my interests lie in controllability and personalization in generative models.

Outside of research, I am a classically trained flutist and enjoy badminton and diving.

news

Apr 01, 2026 One paper accepted to CVPR Findings, many thanks to all collaborators :purple_heart:
Aug 21, 2025 My paper is accepted to EMNLP Findings
Jun 26, 2025 My first paper is accepted to ICCV 2025! :sparkles:

selected publications

  1. CVPR
    handctrl.png
    Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control
    Linxi Xie*, Lisong C. Sun*, Ashley Neall*, and 3 more authors
    2026
    Accepted to CVPR 2026 Findings Track
  2. EMNLP
    machineunlearning.jpg
    Reveal and Release: Iterative LLM Unlearning with Self-generated Data
    Linxi Xie, Xin Teng, Shichang Ke, and 2 more authors
    2025
    Accepted to EMNLP Findings 2025
  3. ICCV
    imagegem.png
    ImageGem: In-the-wild Generative Image Interaction Dataset for Generative Model Personalization
    Yuanhe Guo*, Linxi Xie*, Zhuoran Chen, and 5 more authors
    2025
    Accepted to ICCV 2025