Mingchao Sun (孙铭超)

about

Profile

highlights

News

• 2026.07 Released Abot-World and ABot-3DWorld — a universal world model that explores any 3D space. live demo → news →
• 2026.07 Released WorldRoamBench, an open-world benchmark probing the long-horizon stability of interactive world models. Benchmark homepage → news →
• 2026.06 Released ABot-Earth 0.5, a generative 3D model of the Earth. live demo → news →
• 2026.06 SocialNav, a human-inspired foundation model for socially-aware navigation — selected as a CVPR 2026 Best Paper Candidate! project → news →
• 2026.05 🏆 Won 1st place at the AGIBOT World Model Challenge. news →
• 2026.03 From Orbit to Ground accepted to CVPR 2026 Findings — generative city-scale photogrammetry from extreme off-nadir satellite imagery. project → news →
• 2026.02 Two papers accepted to CVPR 2026 — PointCNN++ (convolution on native points) and SocialNav (socially-aware navigation).
• 2026.02 CLoD-GS accepted to ICLR 2026 — continuous level-of-detail rendering built on 3D Gaussian Splatting.
• 2025.08 "Yunjing" (云境), AMap's immersive AI product — sharing its core capabilities and AMap's recent advances in digital-twin technology and applications. news →

selected work

Publications

sorted by date (newest first)

• 

  ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

  F Jiang, Z Sun, M Wang, Z Zhu, C Wang, Y Zhang, W Liu, Y Wang, et al. Fan Jiang, Zhaoxu Sun, Mengchao Wang, Ziyu Zhu, Chiyu Wang, Yunpeng Zhang, Wenlin Liu, Yun Wang, Xue Zheng, Rui Sun, Junfeng Ni, Hongyu Pan, Zhongxu Sun, Fei Yu, Zengye Ge, Mengmeng Du, Nianfei Fan, Mingchao Sun, Yu Liu, Yongchang Zhang, Yanqing Zhu, Jiahang Wang, Ning Ying, Yuze Xuan, Di Yang, Zhicheng Liu, Zhe Gao, Tingbing Xu, Jiacheng Sui, Wenjin Yang, Junnan Lai, Shufeng Liu, Yuan Liu, Zheng Zhou, Yingliang Peng, Dawei Cao, Kaifeng Sheng, Yuxiang Cai, Fei Lu, Mu Xu, Ning Guo

  Technical Report · 2026

  An action-conditioned video world model enabling real-time, long-horizon closed-loop interaction, trained on AAA games, simulators, and web video.

• 

  ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space

  M Sun, L Tang, Y Liu, X Yan, Z Li, Y Zhang, F Yu, Z Ge, Y Liu, J Zhang, et al. Mingchao Sun, Luyang Tang, Yu Liu, Xu Yan, Zhan Li, Yunwei Zhang, Fei Yu, Zengye Ge, Yumin Liu, Jiacheng Zhang, Yongchang Zhang, Jiawei Zhang, Zhicheng Liu, Zhongxu Sun, Tianjian Ouyang, Wenzheng Chen, Shixing Yang, Nianfei Fan, Guodong Sun, Huan Li, Zheng Zhou, Yongze Li, Yingliang Peng, Mengmeng Du, Yuan Liu, Haozhe Shi, Chunnuo Gong, Chengzhen Yu, Chunxue Jia, Yang Liu, Shiying Zeng, Junnan Lai, Hang Zhang, Ning Guo, Baoquan Chen, Mu Xu, Hongyu Pan

  Technical Report · 2026

  A universal multimodal 3D world model that turns text, image, and video inputs into high-fidelity, explorable 3D worlds.

• 

  ABot-N1: Toward a General Visual-Language Navigation Foundation Model

  R Gong, Y Guo, J Hu, J Kong, X Leng, T Li, W Li, F Liu, Z Liu, J Lu, M Luo, et al. Ruiyan Gong, Yingnan Guo, Junjun Hu, Jintao Kong, Xiaoxu Leng, Tianlun Li, Weize Li, Fei Liu, Zhicheng Liu, Jia Lu, Minghua Luo, Chenlin Ming, Yanfen Shen, Jiyue Tao, Zhengbo Wang, Mingyang Yin, Minqi Gu, Zihao Guan, Wei Guo, Guoqing Liu, Huachong Pang, Menglin Yang, Zeqian Ye, Xiaoxiao Geng, Zhining Gu, Honglin Han, Di Jing, Hongyu Pan, Mingchao Sun, Kuan Yang, Jianfang Zhang, Yanghong Chen, Ye He, Wei Mei, Jiahao Shi, Xiangpo Yang, Yanqing Zhu, Yang Cai, Jingjing Ma, Shihui Su, Zixiao Tang, Linbo Zheng, Zedong Chu, Xiaolong Wu, Wenbin Tang, Mu Xu

  Technical Report · 2026

  A step toward a general Visual Language Navigation foundation model, decoupling cognition from control via a slow-fast architecture guided by dual visual-language signals.

• 

  WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models

  TB Xu, J Sui, Z Gao, K Shi, W Yang, Z Liu, Z Sun, M Sun, H Pan, F Jiang, et al. Ting-Bing Xu, Jiacheng Sui, Zhe Gao, Kewei Shi, Wenjin Yang, Zhicheng Liu, Zhaoxu Sun, Mingchao Sun, Hongyu Pan, Fan Jiang, Mu Xu, Qi Fan, Yang Gao, Yong Li, Baoquan Chen

  Benchmark · 2026

  A benchmark probing long-horizon stability of interactive world models.

• 

  ABot-EARTH 0.5: Generative 3D Earth Model

  M Qian, T Ouyang, M Sun, Z Wang, J Xiong, J Han, Y Zhang, J Zhang, et al. Ming Qian, Tianjian Ouyang, Mingchao Sun, Zijian Wang, Jincheng Xiong, Jiarong Han, Yongchang Zhang, Jiawei Zhang, Xu Wang, Yu Liu, Luyang Tang, Fei Yu, Zengye Ge, Mengmeng Du, Yuan Liu, Nianfei Fan, Song Wang, Yingliang Peng, Chunxue Jia, Yang Liu, Shiying Zeng, Haozhe Shi, Junnan Lai, Hongyu Pan, Zheng Wu, Ning Guo, Mu Xu, Hang Zhang

  Technical Report · 2026

  A generative 3D framework that synthesizes vast, seamless 3D environments from ubiquitous, geospatially referenced satellite imagery.

• 

  POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation

  R Gong, M Zhang, Y Zhao, M Sun, Y Shen, Z Chu, Z Gu, W Guo, X Cheng, et al. Ruiyan Gong, Meisheng Zhang, Yuxiang Zhao, Mingchao Sun, Yanfen Shen, Zedong Chu, Zhining Gu, Wei Guo, Xiaolong Cheng, Qiming Li, Kangning Niu, Yanqing Zhu, Xiaolong Wu, Tianlun Li, Mu Xu

  arXiv · 2026

  The first closed-loop benchmark for real-world POI-goal navigation, paired with a Brain-Action Framework that couples reasoning with continuous waypoint prediction.

• 

  Abot-n0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation

  Z Chu, S Xie, X Wu, Y Shen, M Luo, Z Wang, F Liu, X Leng, J Hu, M Yin, et al. Zedong Chu, Shichao Xie, Xiaolong Wu, Yanfen Shen, Minghua Luo, Zhengbo Wang, Fei Liu, Xiaoxu Leng, Junjun Hu, Mingyang Yin, Jia Lu, Yingnan Guo, Kai Yang, Jiawei Han, Xu Chen, Yanqing Zhu, Yuxiang Zhao, Xin Liu, Yirong Yang, Ye He, Jiahang Wang, Yang Cai, Tianlin Zhang, Li Gao, Liu Liu, Mingchao Sun, Fan Jiang, Chiyu Wang, Zhicheng Liu, Hongyu Pan, Honglin Han, Zhining Gu, Kuan Yang, Jianfang Zhang, Di Jing, Zihao Guan, Wei Guo, Guoqing Liu, Di Yang, Xiangpo Yang, Menglin Yang, Hongguang Xing, Weiguo Li, Mu Xu

  Technical Report · 2026

  A unified Vision-Language-Action (VLA) foundation model that achieves a "Grand Unification" across 5 core tasks.

• 

  From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images

  F Yu, Y Liu, L Tang, M Sun, Z Ge, R Bu, Y Jin, H Zhao, H Sun, Y Li, M Xu, et al. Fei Yu, Yu Liu, Luyang Tang, Mingchao Sun, Zengye Ge, Rui Bu, Yuchao Jin, Haisen Zhao, He Sun, Yangyan Li, Mu Xu, Wenzheng Chen, Baoquan Chen

  CVPR 2026 Findings · 2026

  Generative city-scale photogrammetry from extreme off-nadir satellite imagery.

• 

  PointCNN++: Performant Convolution on Native Points

  L Li, H Zhong, R Bu, M Sun, W Chen, B Chen, Y Li

  CVPR · 2026

  A performant convolution operator that works directly on native point clouds.

• 

  SocialNav: Training a Human-Inspired Foundation Model for Socially-Aware Embodied Navigation

  Z Chen, Y Guo, Z Chu, M Luo, Y Shen, M Sun, J Hu, S Xie, Y Kuan, P Shi, et al. Ziyi Chen, Yingnan Guo, Zedong Chu, Minghua Luo, Yanfen Shen, Mingchao Sun, Junjun Hu, Shichao Xie, Kuan Yang, Pei Shi, Zhining Gu, Lu Liu, Honglin Han, Xiaolong Wu, Mu Xu, Yu Zhang, Ning Guo

  CVPR · 2026

  A human-inspired foundation model for socially-aware embodied navigation.

  ★ CVPR 2026 Best Paper Candidate
• 

  CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting

  Z Cheng, M Sun, Y Liu, Z Ge, L Tang, M Xu, Y Li, P Pan

  ICLR · 2026

  A framework that integrates a continuous LoD mechanism directly into a 3DGS representation.

• 

  DO-Conv: Depthwise Over-Parameterized Convolutional Layer

  J Cao, Y Li, M Sun, Y Chen, D Lischinski, D Cohen-Or, B Chen, C Tu

  IEEE TIP · 2022 351 citations

  A depthwise over-parameterized convolutional layer that boosts 2D CNN backbones.

• 

  DeepPipes: Learning 3D Pipelines Reconstruction from Point Clouds

  L Cheng, Z Wei, M Sun, S Xin, A Sharf, Y Li, B Chen, C Tu

  Graphical Models · 2020 50 citations

  Reconstructing 3D pipeline structures from point clouds.

• 

  Mutual Information Maximization in Graph Neural Networks

  X Di, P Yu, R Bu, M Sun

  IJCNN · 2020 37 citations

  A mutual-information maximization objective for graph neural networks.

• 

  PointCNN: Convolution on X-Transformed Points

  Y Li, R Bu, M Sun, W Wu, X Di, B Chen

  NeurIPS · 2018 4,357 citations

  A foundational convolution operator for deep learning on point clouds.

  ★ 2021 WAIC Youth Outstanding Paper Award

experience

Experience

1. Alibaba Group — AMap, Visual Technology Center 2021.11 – present

   Researcher

   HD Map · 3DGS · World Models

2. Alibaba Group · Alibaba Cloud, Video Cloud & DingTalk 2020.07 – 2021.11

   Algorithm Engineer

   Face & Video Algorithms

3. Alibaba Group · AI Labs 2018.08 – 2020.07

   Research Intern

   Autonomous Driving & V2X

4. Microsoft Research Asia (MSRA) 2016.08 – 2017.04

   Research Intern

   Machine Learning & BI

1. Shandong University 2017.09 – 2020.07

   M.Eng. · Computer Science & Technology · advised by Prof. Baoquan Chen

2. Shandong University 2013.09 – 2017.07

   B.Eng. · Software Engineering

openings

Join the team