Yuntian Deng | 邓云天

I am an undergraduate student in Electrical and Computer Engineering at Shanghai Jiao Tong University. I am a core member of the SJTU Supercomputer Team and an intern at Galbot.

My interests lie at the intersection of Embodied AI and High-Performance AI Systems. I work on robot-learning algorithms, AI infrastructure, and efficient large-model inference—from research prototypes to system-level optimization, with the goal of building real-time-responsive, physics-aware embodied agents.

Profile artwork for Yuntian Deng

Research Interests

Embodied Intelligence. Vision-Language-Action models, world-action models, and learning methods that improve robotic manipulation in complex environments.

Efficient AI Systems. Distributed inference, compilation, quantization, operator optimization, and CPU–GPU scheduling for scientific and foundation models.

Publication

*: joint first author; †: project lead; ✉: corresponding author(s)
A robot manipulating objects in a cluttered scene

Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning

Yixin Zheng*, Jiangran Lyu*,†, Yifan Zhang, Jiayi Chen, Mi Yan, Yuntian Deng, Xuesong Shi, Xiaoguang Zhao, Yizhou Wang, Zhizheng Zhang, He Wang
Robotics: Science and Systems (RSS), 2026   🏆 Best Paper Finalist
arXiv / project page

A dynamics-aware policy-learning framework that enables robots to exploit environmental contacts and object interactions in cluttered scenes.

Experience

Full CV →

SJTU Supercomputer Team Xflops

Core Member · 2024.10–Present

Compete in ASC and SCC International Supercomputer Contest. Optimize large-scale software through operator reconstruction, profiling, and multi-thread scheduling. Maintain the team’s open-source HPC Start Guide. Independently deployed DeepSeek-R1-671B on the SJTU "Zhiyuan-1" TPU Cluster.

Galbot

Embodied AI Algorithm Research Intern

Researched World Action Model (WAM) for robotic manipulation. The work focused on improving robot-arm performance and generalization in complex real-world scenarios through embodied model and manipulation-pipeline research.

Awards

  • 2026 First Prize & Best Presentation Prize, ASC Student Supercomputing Challenge
  • 2025 World Champion Player, ASC Student Supercomputing Challenge
  • 2025 National Scholarship & John Wu & Jane Sun Excellence Scholarship
  • 2023 National First Prize, 37th China Adolescence Science & Innovation Contest

Miscellaneous

  • Assistant manager in the International Program Office of SJTU Global College. Supported cross-cultural activities, welcomed exchange students, and helped them understand Chinese culture, adapt to campus life, and find local community resources.
  • Passionate about fine-art photography, with a focus on urban scenes, campus life, and visual storytelling. Regularly served as a photographer for school events.
  • Enjoy football, badminton, table tennis, and other team or racket sports, and actively participate in sports competitions.