Ran Ding

About Me

I am a PhD student at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), advised by Prof. Ivan Laptev and Dr. Fabio Pizzati.

Previously, I earned an MSc in Computer Science from the Technical University of Munich and a BEng in Computer Science from Dalian University of Technology.

I am interested in multimodal learning, with the goal of advancing physical AGI.

In my spare time, I enjoy cycling and traveling.

News

Oct 2026Memory before Goal is on arXiv: paper, project page, code and dataset.
Sep 2026MessyKitchens (ECCV 2026, Malmö, Sweden) is open-sourced: code and dataset.
Aug 20263D-CovDiffusion (IROS 2026, Pittsburgh, USA) is open-sourced: code and dataset.
Jul 2026TARGO (IJCV 2026) is open-sourced: code, dataset and TARGO-Net model.
Aug 2025Started my PhD at MBZUAI with Prof. Ivan Laptev.

Research

(* and ^† indicate co-first authorship and corresponding author, respectively.)

Memory before Goal: Role of Pre-History Memory for Humanoid Loco-Manipulation

Chenyuan Chen, Ran Ding, Lechen Zhang, Zewen He, Yoshihiko Nakamura

arXiv preprint, 2026

Humanoid Loco-Manipulation Memory Visual Language Action Model

Project Page Paper Code ★3 Data ↓476/mo BibTeX

@misc{chen2026memorybeforegoal,
  title         = {Memory before Goal: Role of Pre-History Memory for Humanoid Loco-Manipulation},
  author        = {Chen, Chenyuan and Ding, Ran and Zhang, Lechen and He, Zewen and Nakamura, Yoshihiko},
  year          = {2026},
  eprint        = {2610.31166},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url           = {https://arxiv.org/abs/2610.31166}
}

Can a humanoid act on something it saw seconds ago but can no longer see? WholeBodyMem selects memory frames from object events for a Unitree G1, evaluated on HuMeGo, a memory-dependent benchmark with 6 simulated and 6 real-world tasks.

MessyKitchens: Contact-rich object-level 3D scene reconstruction

Junaid Ahmed Ansari*, Ran Ding*, Fabio Pizzati, Ivan Laptev

European Conference on Computer Vision (ECCV), 2026

Physically Plausible Generation 3D Reconstruction Simulation Contact-rich Scenes

Project Page Paper Code ★3 Data ↓737/mo Video BibTeX

@inproceedings{ansari2026messykitchens,
  title     = {MessyKitchens: Contact-rich Object-level 3D Scene Reconstruction},
  author    = {Ansari, Junaid Ahmed and Ding, Ran and Pizzati, Fabio and Laptev, Ivan},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year      = {2026},
  url       = {https://arxiv.org/abs/2603.16868}
}

MessyKitchens provides high-quality synthetic training data and real-world test scenes for contact-rich kitchen reconstruction, with improved registration and reduced inter-object penetration. Built on it, MOD achieves state-of-the-art reconstruction and physical metrics.

3D-Aware Diffusion Policy for Coverage Path Planning

Chenyuan Chen, Haoran Ding, Ran Ding, Tianyu Liu, Zewen He, Anqing Duan, Yoshihiko Nakamura

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026

Spatial Robot Policy Industrial Application

Project Page Paper Code ★6 Data ↓873/mo Video BibTeX

@inproceedings{chen2026_3dcovdiffusion,
  title     = {{3D-CovDiffusion}: 3D-Aware Diffusion Policy for Coverage Path Planning},
  author    = {Chen, Chenyuan and Ding, Haoran and Ding, Ran and Liu, Tianyu and He, Zewen and Duan, Anqing and Nakamura, Yoshihiko},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year      = {2026},
  url       = {https://arxiv.org/abs/2510.03011}
}

3D-CovDiffusion introduces a 3D-aware diffusion policy for coverage path planning, aiming to improve coverage behavior through stronger 3D geometric understanding.

TARGO: Benchmarking Target-driven Object Grasping under Occlusions

Ran Ding*, Ziyuan Qin*, Yan Xia*^†, Guanqi Zhan, Kaichen Zhou, Long Yang, Hao Dong, Daniel Cremers

International Journal of Computer Vision (IJCV), 2026

Simulation Spatial Robot Policy Contact-rich Scenes

Project Page Paper Code ★14 Data ↓758/mo Model Video BibTeX

@article{xia2026targo,
  title   = {TARGO and TARGO-Net: Benchmarking Target-Driven Object Grasping Under Occlusions},
  author  = {Xia, Yan and Ding, Ran and Qin, Ziyuan and Zhan, Guanqi and Zhou, Kaichen and Yang, Long and Dong, Hao and Cremers, Daniel},
  journal = {International Journal of Computer Vision},
  year    = {2026},
  doi     = {10.1007/s11263-025-02716-9}
}

This work introduces TARGO, a benchmark dataset for target-driven grasping under occlusions in cluttered environments, along with TARGO-Net to improve grasping performance in these physically challenging settings.

Projects

Chinese Undergraduate Curling AI Challenge

Robotics System

Video

We refined motion strategies for a curling robot and implemented a neural network regression model to predict the relationship between robot velocity and current position.

National Undergraduate Electronic Design Contest

Robotics System

Report

We developed a paper counting device using least squares fitting to correlate paper quantity and capacitance measurements from the FDC2214 sensor.

National Undergraduate Electronic Design Contest

Robotics System

Album

We developed a target tracking system that controls a vehicle to follow a predefined path and parses data exchanged with a millimeter-wave radar.

Awards

Allianz Scholarship (33,600 Euros, awarded to 8 top students nationwide in Germany), Oct 2022
National Third Prize in National Undergraduate Electronic Design Contest, Sep 2020
National Second Prize in Chinese Undergraduate Computer Design Contest - AI Challenge, Aug 2020
National Second Prize in Chinese Undergraduate Curling AI Challenge, Jul 2020

Ran Ding

About Me

News

Research

Memory before Goal: Role of Pre-History Memory for Humanoid Loco-Manipulation

MessyKitchens: Contact-rich object-level 3D scene reconstruction

3D-Aware Diffusion Policy for Coverage Path Planning

TARGO: Benchmarking Target-driven Object Grasping under Occlusions

Projects

Unsupervised Multi-View Stereo with Neural Radiance Field

Deformation Generation via Autoregressive Models

Chinese Undergraduate Curling AI Challenge

National Undergraduate Electronic Design Contest

National Undergraduate Electronic Design Contest

Awards