Welcome to my homepage! I am Yifan Liu, an undergraduate student majoring in Mathematics & Physics and Measurement Control Technology in Tsinghua University, Beijing, China. My research experience includes 3D computer vision (pointcloud, Gaussians, avatar, language grounding), Multimodal LLMs (architecture and application), vision for robotics, and RL. My aspiration is to build an interactive education AI that can provide qualititive and personalized education to every child in the world.

🔥 News

• 2025.06:  Start working as a visiting research intern at Harvard University.
• 2025.06:  🎉🎉 My first first-author paper is accepted by ICCV25.
• 2024.03:  🎉🎉 The first paper I participated in is accepted as Highlight by CVPR24.

📝 Publications

ICCV25

Learning Efficient and Generalizable Human Representation with Human Gaussian Model

Yifan Liu*, Shengjun Zhang*, Chensheng Dai, Yang Chen, Hao Liu, Chen Li, Yueqi Duan

Paper Project Page

• ICCV 2025
• Feed-forward Gaussians for animatable human avatar.
• Introduces Human Gaussian graph to efficiently model and integrate the relationship between Gaussians from different frames in a video.

LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer

Yipeng Zhang*, Yifan Liu*, Zonghao Guo, Yidan Zhang, Xuesong Yang, Xiaoying Zhang, Chi Chen, Jun Song, Bo Zheng, Yuan Yao, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun

Paper Code

• arxiv preprint, 2024.
• Proposes Inverse Semantic Pyramid to address the single-granularity problem in MLLM visual perception.
• Introduces VDIM and Hiwin attention to construct and integrate high-resolution semantic pyramid.
• Achieves an average of 3.7% performance improvement on 14 MLLM benchmarks.

CVPR24 Highlight

MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection

Haowen Sun, Yueqi Duan, Juncheng Yan, Yifan Liu, Jiwen Lu

Paper

• CVPR 2024 (Highlight)
• Introduce 2D pretrain models to 3D indoor scene segmentation.
• Propose a novel Mirage Projection method to tackle occlusion problems in 3D scenes.

📖 Educations

• 2022.08 - (now), Undergraduate Student at Tsinghua University, Beijing, China. Majoring in Electronic Engineering and Mathematics & Physics (double major). Doing research in 3D Vision in Prof. Yueqi Duan’s group.
• 2019.09 - 2022.07, High school student at No.2 High School of East China Normal University. Marvelous experience! Member of the school’s Physics Olympiad team and got a national 🥈 in the 38th Chinese Physics Olympiad.

💻 Internships

• Visiting Undergraduate Research Intern at VCG, Harvard University. Working on vision for robotics and 3D for embodied AI with Prof. Hanspeter Pfister.
• Remote Research Intern at Katef Group, Carnegie Mellon University. Working on 3D language grounding and vision for Embodied AI with Prof. Katerina Fragkiadaki.
• Research Intern at THUNLP, Tsinghua University. Working on basic visual architecture of Multimodal LLMs with Prof. Zhiyuan Liu.
• Research Intern at i-Vision Group, Tsinghua University. Working on point cloud perception, Gaussian reconstruction and 3D gaussian avatar with Prof. Yueqi Duan.