# Mark He Huang

> Computer Science PhD student based in Singapore, working on 3D/4D perception, learning, and reasoning in physical spaces.

## Biography

Hi there, I'm Mark He Huang, currently based in Singapore. I work on 3D/4D perception, learning, and reasoning in physical spaces. I'm a PhD student in Computer Science at [Singapore University of Technology and Design](https://www.sutd.edu.sg/), and my PhD research is generously supported by [A*STAR](https://www.a-star.edu.sg/) Computing and Information Science (ACIS/AGS Computing) Scholarship.

## Publications

### Physical Simulator In-the-Loop Video Generation

- Venue: CVPR 2026
- Authors: [Lin Geng Foo](https://lingeng.foo/), [Mark He Huang](https://markhh.com/), [Alexandros Lattas](https://alexlattas.com/), [Stylianos Moschoglou](https://scholar.google.com/citations?user=bMuT5mkAAAAJ&hl=en), [Thabo Beeler](https://thabobeeler.com/), [Christian Theobalt](https://people.mpi-inf.mpg.de/~theobalt/)
- Resources: [project](https://vcai.mpi-inf.mpg.de/projects/PSIVG/) · [code](https://github.com/MarkHershey/PSIVG) · [arXiv:2603.06408](https://arxiv.org/abs/2603.06408)
- Stable ID: `foo2026physical`

```bibtex
@article{foo2026physical,
  title={Physical Simulator In-the-Loop Video Generation},
  author={Foo, Lin Geng and Huang, Mark He and Lattas, Alexandros and Moschoglou, Stylianos and Beeler, Thabo and Theobalt, Christian},
  journal={arXiv preprint arXiv:2603.06408},
  year={2026}
}
```

### OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects

- Venue: NeurIPS 2025 (Spotlight)
- Authors: [Mark He Huang](https://markhh.com/), [Lin Geng Foo](https://lingeng.foo/), [Christian Theobalt](https://people.mpi-inf.mpg.de/~theobalt/), [Ying Sun](https://scholar.google.com.sg/citations?user=AJReaQ8AAAAJ&hl=en), [De Wen Soh](https://www.sutd.edu.sg/profile/soh-de-wen/)
- Resources: [project](https://markhh.com/OnlineSplatter/) · [arXiv:2510.20605](https://arxiv.org/abs/2510.20605)
- Stable ID: `huang2025onlinesplatter`

```bibtex
@article{huang2025onlinesplatter,
  title={OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects},
  author={Huang, Mark He and Foo, Lin Geng and Theobalt, Christian and Sun, Ying and Soh, De Wen},
  journal={arXiv preprint arXiv:2510.20605},
  year={2025}
}
```

### Learning to Unlearn for Robust Machine Unlearning

- Venue: ECCV 2024
- Authors: [Mark He Huang](https://markhh.com/), [Lin Geng Foo](https://lingeng.foo/), [Jun Liu](https://scholar.google.com/citations?user=Q5Ild8UAAAAJ)
- Resources: [paper](https://arxiv.org/abs/2407.10494) · [arXiv:2407.10494](https://arxiv.org/abs/2407.10494)
- Stable ID: `huang2024learning`

```bibtex
@inproceedings{huang2024learning,
  title={Learning to Unlearn for Robust Machine Unlearning},
  author={Huang, Mark He and Foo, Lin Geng and Liu, Jun},
  booktitle={European Conference on Computer Vision},
  year={2024},
  organization={Springer}
}
```

### Meta Compositional Referring Expression Segmentation

- Venue: CVPR 2023
- Authors: [Li Xu](https://scholar.google.com/citations?user=eZWXOqYAAAAJ), [Mark He Huang](https://markhh.com/), [Xindi Shang](https://xdshang.github.io/), [Zehuan Yuan](https://shallowyuan.github.io/), [Ying Sun](https://scholar.google.com.sg/citations?user=AJReaQ8AAAAJ&hl=en), [Jun Liu](https://scholar.google.com/citations?user=Q5Ild8UAAAAJ)
- Resources: [paper](https://openaccess.thecvf.com/content/CVPR2023/html/Xu_Meta_Compositional_Referring_Expression_Segmentation_CVPR_2023_paper.html) · [arXiv:2304.04415](https://arxiv.org/abs/2304.04415)
- Stable ID: `xu2023meta`

```bibtex
@inproceedings{xu2023meta,
  title={Meta Compositional Referring Expression Segmentation},
  author={Xu, Li and Huang, Mark He and Shang, Xindi and Yuan, Zehuan and Sun, Ying and Liu, Jun},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={19478--19487},
  year={2023}
}
```

### SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events

- Venue: CVPR 2021
- Authors: [Li Xu](https://scholar.google.com/citations?user=eZWXOqYAAAAJ), [He Huang](https://markhh.com/), [Jun Liu](https://scholar.google.com/citations?user=Q5Ild8UAAAAJ)
- Resources: [paper](https://openaccess.thecvf.com/content/CVPR2021/html/Xu_SUTD-TrafficQA_A_Question_Answering_Benchmark_and_an_Efficient_Network_for_CVPR_2021_paper.html) · [dataset](https://github.com/SUTDCV/SUTD-TrafficQA) · [arXiv:2103.15538](https://arxiv.org/abs/2103.15538)
- Stable ID: `xu2021sutd`

```bibtex
@inproceedings{xu2021sutd,
  title={SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events},
  author={Xu, Li and Huang, He and Liu, Jun},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={9878--9888},
  year={2021}
}
```

## Scholarly and social profiles

- [Google Scholar](https://scholar.google.com/citations?user=lv1uAiMAAAAJ)
- [ORCID](https://orcid.org/0000-0002-9217-4977)
- [OpenReview](https://openreview.net/profile?id=~Mark_He_Huang1)
- [arXiv](https://arxiv.org/a/huang_h_7.html)
- [ResearchGate](https://www.researchgate.net/profile/He-Huang-106)
- [DBLP](https://dblp.org/pid/344/4694.html)
- [LinkedIn](https://www.linkedin.com/in/markhehuang/)
- [GitHub](https://github.com/MarkHershey)
- [Instagram](https://www.instagram.com/markkkhh/)
- [X.com](https://x.com/markkkhh)
- [GPG Public Key](https://markhh.com/GPG.txt)

## Website metadata

- Canonical website: [https://markhh.com/](https://markhh.com/)
- Google Scholar: [Full publication list](https://scholar.google.com/citations?user=lv1uAiMAAAAJ)
- Agent-oriented index: [llms.txt](https://markhh.com/llms.txt)
- Last updated: July 2026