PERSONAL RESEARCH HOMEPAGESINGAPORE · NTU

PHYSICAL AI & EMBODIED AI

Runmao Yao.

Understanding the
physical world.

PhD Student at MMLab@NTU
Advised by Prof. Ziwei Liu

Portrait of Runmao Yao
RUNMAO YAONTU · SG
PERCEPTION → REASONING → ACTION
EXPLORING INTELLIGENCE IN THE PHYSICAL WORLDSCROLL TO EXPLORE

01 / ABOUT

Curiosity,
grounded in
the real world.

I am a PhD Student at MMLab@NTU, supervised by Prof. Ziwei Liu. I received my Bachelor of Engineering degree from the School of Software, Tsinghua University.

During my undergraduate studies, I was fortunate to work with Prof. Yu-Shen Liu and Prof. Chen Wang, whose guidance has shaped my academic journey.

My research lies in Physical AI and Embodied AI.

Feel free to reach out for collaborations, questions, or just to chat!

yaorunmao@gmail.com

02 / UPDATES

Latest
news.

New work and milestones.

  • Sep 30, 2026EgoTools is out — a 100-hour egocentric dataset and diagnostic benchmark for tool-centric reasoning in real-world videos.
  • Aug 27, 2026Code as Worlds is out — introducing executable world representations for grounded physical reasoning.
  • Aug 10, 2026Started my Ph.D. at MMLab@NTU, advised by Prof. Ziwei Liu.
  • Jul 30, 2026ACE-Data-0 is out — a large-scale, long-horizon, multimodal dataset for household human-object and human-scene interactions.
Earlier updates
  • Jul 17, 2026Apple-π is out — the first benchmark for evaluating law-grounded physical reasoning in video models.
  • Jun 18, 2026S-Agent is out — a spatial tool-use agent for continuous multi-view image and video reasoning.
  • May 26, 2026SpatialBench is out — a cross-paradigm benchmark for evaluating spatial foundation models.
  • May 20, 2026PhysX-Omni is out — a unified framework for simulation-ready physical 3D asset generation.
  • Jan 23, 2026AnchoredDream is out — zero-shot 360° indoor scene generation from a single image.
  • Sep 28, 2025Joined MMLab@NTU as a Research Assistant.
  • Jun 21, 2025Graduated from Tsinghua University with a B.Eng. in Software Engineering.
  • Mar 18, 2025SuperPC is out — a single diffusion model for point cloud completion, upsampling, denoising, and colorization.
  • Mar 03, 2025AirRoom is out — an object-aware approach to room reidentification.
  • Dec 15, 2024Joined Prof. Yu-Shen Liu's group for my undergraduate thesis.
  • Jul 01, 2024Joined SAIR Lab as a summer research intern.

03 / PUBLICATIONS

Research in
perspective.

Google Scholar
EgoTools teaser: dataset overview, annotations, and tool-use reasoning benchmark
RESEARCH / 01EMNLP 2026

EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos

Shulin Tian*, Junsu Kim*, Shuai Liu*, Hao Li*, Yujiao Shen, Sihan Li, Zhe Yang, Yeongon Kim, Feiyu Li, Jialin Wu, Yichi Zhang, Wenhui Wang, Runmao Yao, Yuhao Dong, Zhaoxi Chen, Fangzhou Hong, Antonino Furnari, Jingkang Yang, Hongyuan Zhu, Ziwei Liu

Paper Code Project
Code as Worlds
RESEARCH / 02Technical Report

Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning

Hanyang Wang, Yimo Cai, Weiliang Chen, Jiawei Chi, Haowen Sun, Qiyu Dai, Yi-Hsin Hung, Xingzhuo Guo, Jinshan Ren, Runmao Yao, Ziwei Liu, Mingsheng Long, Yueqi Duan, Jun Gao, Jiangran Lyu, Fangfu Liu, Jialong Wu

Paper Code Project
ACE-Data-0
RESEARCH / 03Technical Report

ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine

Yukang Cao*, Haozhe Xie*, Beichen Wen*, Runmao Yao, Yinghao Liu, Yue Huang, Zhichao Liao, Yunxiang Wang, Haiheng Liu, Xingshun Tian, Dawei Su, Long Zhuo, Dacheng Tao, Xiaogang Wang, Liang Pan, Ziwei Liu

Paper Dataset Project
Apple-π
RESEARCH / 04NeurIPS 2026

Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence

Runmao Yao*, Kairui Hu*, Yukang Cao, Ruisi Wang, Shulin Tian, Ziang Cao, Weichen Fan, Ziqi Huang, Yuhao Dong, Hao Li, Zhaoxi Chen, Zhongang Cai, Lei Yang, Ziwei Liu

Paper Code Project
S-Agent
RESEARCH / 05arXiv 2026

S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence

Yalun Dai*, Hao Li*, Shulin Tian, Runmao Yao, Yuhao Dong, Fangzhou Hong, Zhaoxi Chen, Fangfu Liu, Baoliang Tian, Dingwen Zhang, Tao Wang, Kim-Hui Yap, Ziwei Liu

Paper Code Project
SpatialBench
RESEARCH / 06NeurIPS 2026

SpatialBench: Is Your Spatial Foundation Model an All-Round Player?

Haosong Peng*, Hao Li*, Jiaqi Chen*, Yuhao Pan*, Runmao Yao, Yalun Dai, Fushuo Huo, Fangzhou Hong, Zhaoxi Chen, Haozhao Wang, Dingwen Zhang, Ziwei Liu, Wenchao Xu

Paper Code Project
PhysX-Omni
RESEARCH / 07arXiv 2026

PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects

Ziang Cao, Yinghao Liu, Haitian Li, Runmao Yao, Fangzhou Hong, Zhaoxi Chen, Liang Pan, Ziwei Liu

Paper Code Project
AnchoredDream
RESEARCH / 08arXiv 2026

AnchoredDream: Zero-Shot 360° Indoor Scene Generation from a Single View via Geometric Grounding

Runmao Yao*, Junsheng Zhou*, Zhen Dong, Yu-Shen Liu

Paper
SuperPC
RESEARCH / 09CVPR 2025

SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization

Yi Du, Zhipeng Zhao, Shaoshu Su, Sharath Golluri, Haoze Zheng, Runmao Yao, Chen Wang

Paper Code Project
AirRoom
RESEARCH / 10CVPR 2025

AirRoom: Objects Matter in Room Reidentification

Runmao Yao, Yi Du, Zhuoqun Chen, Haoze Zheng, Chen Wang

Paper Code Project

04Honors and Awards

  • 2024
    • Sep Comprehensive Excellence Award (Top 5%) Tsinghua University
  • 2023
    • Sep Comprehensive Excellence Award (Top 5%) Tsinghua University
  • 2021
    • Dec Second Prize Scholarship for Incoming Students (Top 5%) Tsinghua University

05Education

  • 2026.08 - Present Ph.D. College of Computing and Data Science, Nanyang Technological University Singapore
  • 2021.09 - 2025.06 B.Eng. School of Software, Tsinghua University Beijing, China

06Experience

  • 2026.08 - Present Research Collaborator ByteDance PICO, Beijing, China
  • 2025.09 - 2026.07 Research Assistant MMLab@NTU, Singapore