prof_pic.jpg

Xinyang Liu (刘昕洋)

Master student
School of Electronic Engineering
Xidian University
Email: xinyangATK [AT] gmail [dot] com
Google scholar | Github | Twitter

Bio

Howdy! I am a research intern at Purdue University, advised by Prof. Ruqi Zhang. I’m also work closely with Prof. Mingyuan Zhou, an Associate Professor at the University of Texas at Austin. I received my M.S degree from Xidian University in 2024, advised by Prof. Bo Chen. Previously, I obtained my B.S degree from Xidian University in 2021.

My research interests lie in the general area of machine learning, particularly in solving practical problems through advanced Generative AI systems. My recent researches focus on Generative Modeling, including its theoretical exploration and various applications in data generation and multi/cross-modal learning.

:fire::fire::fire: Now I’m looking for PhD 25 Fall and here is my CV !

In addition, I am very interested in robot learning, planning, and AI4Science within the framework of Generative AI.

If you share the same research interests with me, feel free to reach out or add my WeChat.

news

Jun, 2024 I graduated with a master’s degree in Xidian University!
Apr, 2024 Our paper “Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Models” is accepted by UAI 2024.
Sep, 2023 Two papers are accepted by NeurIPS 2023!
Apr, 2023 Our paper “Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process” is accepted by ICML 2023.
Feb, 2023 :fire::fire::fire: We have open sourced a new version of PyDPM, and welcome to join the open source library of deep probabilistic models!
PyDPM is a python library focuses on constructing Deep Probabilistic Models (DPMs). Our developed Pydpm not only provides efficient distribution sampling functions on GPU, but also has included the implementations of existing popular DPMs.

selected publications

(*) denotes equal contribution

  1. hutch++.png
    Optimal Stochastic Trace Estimation in Generative Modeling
    Xinyang Liu*Hengrong Du*Wei Deng, and Ruqi Zhang
    Under review., 2024
  2. GBD.png
    Advancing Graph Generation through Beta Diffusion
    Xinyang Liu*, Yilin He*, Bo Chen, and Mingyuan Zhou
    Under review. ArXiv 2406.09357, 2024, 2024
  3. PBPrompt.png
    Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Models
    Xinyang Liu*Dongsheng Wang*, Bowei Fang, Miaoge Li, Zhibin Duan, Yishi Xu, Bo Chen, and Mingyuan Zhou
    Proceedings of the 40th Conference on Uncertainty in Artificial Intelligence (UAI), 2024
  4. ProGBN.png
    Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process
    Zhibin Duan*Xinyang Liu*, Yudi Su, Yishi Xu, Bo Chen, and Mingyuan Zhou
    The 40th International Conference on Machine Learning (ICML), 2023