Pinxin Liu

✱ ✦ ✧ ✶

Pinxin Liu

Exploring the convergence of vision, language, and motion

Hi! 👋

I am a PhD student, supervised by Dr. Chenliang Xu, in Computer Science department at University of Rochester. My research interests are Multi-modal Learning and Computer Graphics, including Multi-modal Large Language Models, Digital Human Rendering/Motion Synthesis, and Video Generation.

Previously, I was an undergraduate student who received the highest honor distinction in research Bachelor of Science in Computer Science at the University of Rochester.

RESEARCH INTERESTS

Multi-modal Learning

Vision-language models and multi-modal understanding

Digital Humans

Realistic avatar rendering and animation

Video Generation

Motion synthesis and video creation techniques

Co-Speech Gesture

Generating natural gestures from speech

ACADEMIC JOURNEY

May 2025 - August 2025

Research Scientist Intern, Meta Reality Lab

Jan 2025 - Present

PhD in Computer Science, University of Rochester

May 2024 - Dec 2024

Research Scientist Intern, FlawlessAI

July 2020 - May 2024

BS in Computer Science with Highest Honor, University of Rochester

NEWS

[03/2025] I will join Meta Reality Lab as a Research Scientist Intern.
[11/2024] One first author paper accepted 3DV 2025.
[09/2024] One co-author paper accepted Siggraph Asia 2024.
[07/2024] One first author paper accepted ECCV 2024.
[06/2024] Joined FlawlessAI as a Research Scientist Intern.
[05/2024] I received a BS degree in Computer Science with the Highest Honor Distinction in Research.
[05/2024] One co-authored paper accepted to Interspeech 2024.
[05/2024] One first-authored paper accepted to ACL 2024.
[04/2024] I was honored as the National Student Employee of the Year for 2024, selected from a highly competitive pool of six candidates across the country.
[12/2023] One first-authored paper accepted to ICASSP 2024.
[01/2023] One co-authored paper accepted to AAAI 2021 Workshop.

PAPERS

Contextual Gesture: Co-Speech Gesture Video Generation through Context-aware Gesture Representation Pinxin Liu, Pengfei Zhang, Hyeongwoo Kim, Pablo Garrido, Ari Sharpio and Kyle Olszewski. Arxiv 2025
[Paper] [Project] [Code]
Generative AI for Cel-Animation: A Survey Yunlong Tang, Junjia Guo, Pinxin Liu, Zhiyuan Wang, Hang Hua, Jia-Xing Zhong, Yunzhong Xiao, Chao Huang, Luchuan Song, Susan Liang and 7 more authors. Arxiv 2025
[Paper] [Project]
Video Understanding with Large Language Models: A Survey Yunlong Tang*, Jing Bi*, Siting Xu*, Luchuan Song, Susan Liang, Teng Wang, ...,Pinxin Liu, Mingqian Feng, Feng Zheng, Jianguo Zhang, Ping Luo, Jiebo Luo, and Chenliang Xu. Arxiv 2025
[Paper] [Project]
GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling Pinxin Liu, Luchuan Song, Junhua Huang, Haiyang Liu and Chenliang Xu. Arxiv 2025
[Paper] [Project] [Code]
KinMo: Kinematic-aware Human Motion Understanding and Generation Pinxin Liu*, Pengfei Zhang*, Hyeongwoo Kim, Pablo Garrido and Bindita Chaudhuri. Arxiv 2025
[Paper] [Project] [Code]
GaussianStyle: Gaussian Head Avatar via StyleGAN Pinxin Liu, Luchuan Song, Daoan Zhang, Hang Hua, Yunlong Tang, Huaijin Tu, Jiebo Luo and Chenliang Xu. 3DV 2025
[Paper] [Project] [Code]
Texttoon: Real-time text toonify head avatar from single video Luchuan Song, Lele Chen, Celong Liu, Pinxin Liu, and Chenliang Xu. Siggraph Asia 2024
[Paper] [Project] [Code] [Demo]
Tri^{2}-plane: Thinking Head Avatar via Feature Pyramid Luchuan Song, Pinxin Liu, Lele Chen, Celong Liu and Chenliang Xu. ECCV 2024
[Paper] [Project] [Code] [Demo]
An Empirical Analysis on Large Language Models in Debate Evaluation Xinyi Liu, Pinxin Liu, and Hangfeng He. ACL 2024
[Paper] [Code]
Articulatory Phonetics Informed Controllable Expressive Speech Synthesis Zehua Kcriss Li, Meiying Melissa Chen, Yi Zhong, Pinxin Liu, and Zhiyao Duan. Interspeech 2024
[Paper] [Demo] [Code]
Adaptive Super Resolution For One-Shot Talking-Head Generation Luchuan Song, Pinxin Liu, Guojun Yin, Chenliang Xu. ICASSP 2024
[Paper] [Project] [Code]
Contextualized Multi-Step Commonsense Reasoning through Context Extension Hecong Wang, Erqian Xu, Pinxin Liu, Zijian Meng, Zhen Bai. AAAI Workshop 2023
[Paper]

TEACHING

2024 Spring CSC 2/449: Machine Vision
Instructor: Dr. Chengliang Xu
2023 FALL CSC 446: Machine Learning
Instructor: Dr. Daniel Gildea
2023 SPRING CSC 2/447: Nature Language Processing
Instructor: Dr. Hangfeng He
2022 Fall CSC 2/448: Statistical Speech and Language Processing
Instructor: Dr. Daniel Gildea

REVIEWING

CVPR 2024, 2025, EMNLP 2023, KDD 2024, AAAI 2024, ICLR 2025, 3DV 2025

SKILLS

Programming Languages

Python

C++

Java

Machine Learning

PyTorch

TensorFlow

Deep Learning

NLP

Computer Vision

3D Graphics

Tools & Technologies

CUDA

Linux

Git

LaTeX

Soft Skills

Research Methods

Technical Writing