Yatian Pang εΊžι›…ε€©

Incoming Research Scientist, NVIDIA Deep Imagination Research

Greetings! I am currently completing my Ph.D. at the National University of Singapore. I feel incredibly lucky to be supervised by Prof. E. H. Francis Tay, collaborate closely with Prof. Li Yuan from PKU, and gain valuable experience working with Alibaba's Qwen, Everlyn, and A*STAR.

My long-term goal is to build general-purpose AI systems that seamlessly bridge multi-modal understanding and generation, advancing the frontiers of world models and physical AI.

Email  •  Google Scholar  •  Github  •  Linkedin

profile photo

🎨 Selected Works

Understanding

🌟 Qwen3-VL

Qwen Team, Yatian Pang (2025)

One of the most popular open-sourced VLMs. Key contributions to long and streaming video understanding within the Qwen3-VL framework, achieving SOTA results across multiple video benchmarks.

[Project Page] [Code]

Generation

🌟 Open-Sora-Plan

Open-Sora-Plan Team, Yatian Pang (2024)

Pioneering open-source effort to reproduce Sora. Responsible for the high-resolution, long-duration video generation architecture and curating open-source high-quality video datasets.

[arXiv link] [Code]

Unify

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

Bin Lin, et al., Yatian Pang, Li Yuan (2025)

[arXiv] [Code]

Generation

Next Patch Prediction for Autoregressive Visual Generation

Yatian Pang, et al. (AAAI 2026)

[arXiv] [Code]

Generation

DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses

Yatian Pang, et al. (ICCV 2025)

[arXiv] [Code]

Understanding

MoE-LLaVA: Mixture of Experts for Large Vision-Language Models

Bin Lin, et al., Yatian Pang, et al. (TMM 2024)

[arXiv] [Code]

Understanding

LanguageBind: Extending Video-Language Pretraining to N-Modality by Language-Based Semantic Alignment

Bin Zhu, et al., Yatian Pang, et al. (ICLR 2024)

[arXiv] [Code]

Understanding

Masked Autoencoders for Point Cloud Self-Supervised Learning

Yatian Pang, et al. (ECCV 2022)

[arXiv] [Code]

πŸ’» Work Experience

Nvidia, Singapore

Dec. 2025 - Present, Research Scientist

Alibaba Qwen, China

Apr. 2025 - Nov. 2025, Research Intern. Mentor: Dr. Shuai Bai, Dr. Hang Zhang.

Everlyn, China

Oct. 2024 - Apr. 2025, Researcher. Mentor: Prof. Ser-Nam Lim, Prof. Harry Yang

A*STAR, Singapore

Oct. 2021 - Dec. 2023, Research Engineer & Research Intern. Mentor: Dr. Xiang Li, Prof. Zhenghua Chen

πŸŽ“ Education

National University of Singapore, Singapore

Aug. 2021 - Present, PhD

Peking University, China

Jul. 2023 - Dec. 2024, Visiting Scholar

National University of Singapore, Singapore

Aug. 2020 - Jun. 2021, MSc