Tingrui Shen

I am an undergraduate student in Computer Science at South China University of Technology and an incoming master's student at Peking University. My work focuses on 3D generation, world models, and embodied AI.

I have previously worked at Tencent and VAST, and published papers at conferences including CVPR and ACM MM. Grounded in physics as the fundamental constraint, my long-term goal is to build world models that can generate and evolve reality, and to push embodied intelligence toward real-world closed-loop deployment.

Email / Project Page

News

[March 2026] Started my internship at VAST (Tripo3D).

[Feb 2026] FlashMesh was accepted to CVPR 2026.

[Aug 2025] Panoptic-L3D was accepted to ACM MM 2025.

[Jan 2025] Joined Tencent VISVISE Lab as a research intern.

Research Interests

3D Generation

Geometry, Mesh, and Scene Synthesis

I work on structured generation for 3D assets and scenes.

World Models

Simulation-Oriented Visual Intelligence

I am interested in scalable world modeling for physical and interactive environments.

Embodied AI

Perception, Action, and Data Engines

I care about systems that connect perception, action, and real-world deployment.

Research Experience

Dec 2025 - Present

Embodied Intelligence Research, Peking University

Advisor: Prof. He Wang

Sep 2025 - Present

3D Generation Research, Peking University

Advisor: Prof. Ronggang Wang

Aug 2023 - Present

Vision and Generation Research, SMU

Advisor: Prof. Shengfeng He

Oct 2023 - Feb 2024

Multimodal LLM Research, HUST

Advisor: Prof. Min Chen

Education

Incoming

Peking University

M.S. in Computer Science and Technology · Sep 2026 - Jun 2029 (expected)

Incoming master's student in Shenzhen.

Undergraduate

South China University of Technology

B.Eng. in Computer Science and Technology · Sep 2022 - Jun 2026 (expected)

GPA: 3.91 / 4.0

Publications

FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation

Tingrui Shen*, Yiheng Zhang*, Chen Tang*, Chuan Ping, Zixing Zhao, Le Wan, Yuwang Wang, Ronggang Wang, Shengfeng He

CVPR 2026

arXiv Paper Project

Language-Driven 3D Human Pose Estimation in Multi-Person Scenarios: A New Dataset and Approach

Tingrui Shen, Bangzhen Liu, Zhirun Fan, Shiting Zhang, Weifeng Pan, Sun Fan, Dan Cao, Shengfeng He

ACM MM 2025

Paper Project

LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion

Jiangran Lyu, Kai Liu, Xuheng Zhang, Haoran Liao, Yusen Feng, Wenxuan Zhu, Tingrui Shen, Jiayi Chen, Jiazhao Zhang, Yifei Dong, Wenbo Cui, Senmao Qi, Shuo Wang, Yixin Zheng, Mi Yan, Xuesong Shi, Haoran Li, Dongbin Zhao, Ming-Yu Liu, Zhizheng Zhang, Li Yi, Yizhou Wang, He Wang

Under Review 2026

arXiv Paper Project

QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning

Yiheng Zhang, Zhe Zhu, Tingrui Shen, Zhuojiang Cai, Tianxiao Li, Zixing Zhao, Qiujie Dong, Zhiyang Dou, Jiepeng Wang, Le Wan, Yuwang Wang, Wengping Wang, Yuan Liu, Cheng Lin

Under Review 2026

Links coming soon

DFMU: Distribution-Based Framework for Modeling Aleatoric Uncertainty in Multimodal Sentiment Analysis

Chen Tang*, Tingrui Shen*, Xinrong Gong, Chong Zhao, Tong Zhang

IJCAI 2025

Paper PDF

Towards Trustworthy Model via Uncertainty Verification in Multimodal Sentiment Analysis

Chen Tang, Yangle Li, Tingrui Shen, Xinrong Gong, Tong Zhang

ICME 2025

Paper

Stable Score Distillation

Haiming Zhu, Yangyang Xu, Chenshu Xu, Tingrui Shen, Wenxi Liu, Yong Du, Jun Yu, Shengfeng He

ICCV 2025

arXiv Paper

Teaching Diffusion Models to Ground Alpha Matte

Tianyi Xiang, Weiying Zheng, Yutao Jiang, Tingrui Shen, Hewei Yu, Yangyang Xu, Shengfeng He

TMLR 2025

Paper Project

Projects

Surgical Image Recognition and Segmentation

Collaboration with Kiang Wu Hospital · Algorithm Lead · Apr 2024 - Dec 2024

Built a data pipeline from real surgical footage, including filtering, SAM-based annotation, and downstream model training.

Embodied Medical Intelligence with Multimodal LLM Fine-Tuning

Collaboration with Tongji Medical College, HUST · Project Lead · Oct 2023 - Feb 2024

Curated and enhanced fabric-related multimodal data for fine-tuning large multimodal models in medical settings.

Workshop Gas Leakage Detection

Collaboration with XPeng Motors · Algorithm Lead · Sep 2024 - Oct 2024

Designed a time-series detection and forecasting pipeline using simulation data, filtering, augmentation, and model training.

Industry Experience

Visvise AI Lab, Tencent

Jan 2025 - Nov 2025

Worked on 3D mesh generation, image-to-mesh systems, texture generation, and inference acceleration for production-oriented pipelines.

Tripo3D, VAST

Jan 2026 - Present

Exploring world models for embodied AI, with current projects on data engines and 3D scene reconstruction.

Updated April 2026