Yang Tian (田洋)

Education

• Peking University — Ph.D., School of Software & Microelectronics
  2023 – present · Advised by Prof. Hao Dong and Prof. Ping Wang
• Peking University — B.S., School of Mathematical Sciences
  2019 – 2023

During my internship at Shanghai AI Laboratory, I worked closely with Jiangmiao Pang and Jia Zeng.

Highlights

InternData-A1, the largest open-source synthetic dataset for robotic manipulation (630K trajectories, 7,433 hours), has been downloaded 550K+ times on Hugging Face and 1.65M+ times on ModelScope, and adopted by teams including NVIDIA Cosmos, ByteDance Seed, Qwen, Xiaomi, Tencent, JD, and Ant Lingbo to train their VLA and world models.

Seer (ICLR 2025 Oral) has served as a strong baseline for subsequent research on manipulation policies.

Built on the data and models above, the InternVLA series outperforms π_0.5, π₀, and GR00T N1.5 across real-robot and simulation benchmarks.

Selected publications

• InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy
  Yang Tian*, Yuyin Yang*, Yiman Xie*, Zetao Cai*, Xu Shi*, Ning Gao, Hangxu Liu, Xuekun Jiang, Zherui Qiu, Feng Yuan, Yaping Li, Ping Wang, Junhao Cai, Jia Zeng, Hao Dong, Jiangmiao Pang
  CVPR 2026 Isaac SimNewton
  paper / code / huggingface / modelscope / project
• Seer: Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation
  Yang Tian*, Sizhe Yang*, Jia Zeng, Ping Wang, Dahua Lin, Hao Dong, Jiangmiao Pang
  ICLR 2025 Oral (top 1.9%)
  paper / code / project
• InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation
  InternVLA-A1 Team (incl. Yang Tian, core contributor)
  arXiv 2026
  paper / code / model / project
• InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization
  InternVLA-A1.5 Team (incl. Yang Tian, core contributor)
  arXiv 2026
  paper / code / model / project
• RoboKeyGen: Robot Pose and Joint Angles Estimation via Diffusion-based 3D Keypoint Generation
  Yang Tian*, Jiyao Zhang*, Guowei Huang, Bin Wang, Ping Wang, Jiangmiao Pang, Hao Dong
  ICRA 2024 Blender
  paper / project
• Robot Structure Prior Guided Temporal Attention for Camera-to-Robot Pose Estimation from Image Sequence
  Yang Tian*, Jiyao Zhang*, Zekai Yin*, Hao Dong
  CVPR 2023 Blender
  paper / code / project

* equal contribution

Honors & awards

• 2026EAI-100 Next 20 Rising Star
• 2026EAI-100 Top 10 Dataset (InternData-A1)
• 2025Star Intern Award, the top intern award of Shanghai AI Laboratory
• 2019Top 15 in Shanghai College Entrance Examination (Gaokao)