@article{dong2023dreamllm,
  author = {Dong, Runpei and Han, Chunrui and Peng, Yuang and Qi, Zekun and Ge, Zheng and Yang, Jinrong and Zhao, Liang and Sun, Jianjian and Zhou, Hongyu and Wei, Haoran and Kong, Xiangwen and Zhang, Xiangyu and Ma, Kaisheng and Yi, Li},
  title = {DreamLLM: Synergistic Multimodal Comprehension and Creation},
  journal = {arXiv preprint arXiv:2309.11499},
  year = {2023},
}

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
Zekun Qi, Runpei Dong†, Shaochen Zhang, Haoran Geng, Chunrui Han, Zheng Ge, He Wang, Li Yi, Kaisheng Ma
Project | PDF | Code (coming soon) | BibTex

@article{shapellm24,
  author       = {Zekun Qi and
                  Runpei Dong and
                  Shaochen Zhang and
                  Haoran Geng and
                  Chunrui Han and
                  Zheng Ge and
                  He Wang and
                  Li Yi and
                  Kaisheng Ma},
  title        = {ShapeLLM: Universal 3D Object Understanding for Embodied Interaction},
  journal      = {CoRR},
  volume       = {abs/2402.17766},
  year         = {2024},
  eprinttype    = {arXiv},
  eprint       = {2402.17766},
}

ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning
Liang Zhao*, En Yu*, Zheng Ge, Jinrong Yang, Haoran Wei, Hongyu Zhou, Jianjian Sun, Yuang Peng, Runpei Dong, Chunrui Han, Xiangyu Zhang
PDF | Demo | Code (coming soon) | BibTex

@article{ChatSpot23,
  author       = {Liang Zhao and
                  En Yu and
                  Zheng Ge and
                  Jinrong Yang and
                  Haoran Wei and
                  Hongyu Zhou and
                  Jianjian Sun and
                  Yuang Peng and
                  Runpei Dong and
                  Chunrui Han and
                  Xiangyu Zhang},
  title        = {ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction
                  Tuning},
  journal      = {CoRR},
  volume       = {abs/2307.09474},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2307.09474},
  doi          = {10.48550/arXiv.2307.09474},
  eprinttype    = {arXiv},
  eprint       = {2307.09474},
}

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation
Zekun Qi*, Muzhou Yu*, Runpei Dong†, Kaisheng Ma
NeurIPS 2023 | PDF | Code | BibTex

@inproceedings{
VPP23,
title={{VPP}: Efficient Universal 3D Generation via Voxel-Point Progressive Representation},
author={Zekun Qi and
                  Muzhou Yu and
                  Runpei Dong and
                  Kaisheng Ma},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=etd0ebzGOG}
}

CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP
Junbo Zhang, Runpei Dong, Kaisheng Ma
OpenSUN 3D @ ICCV 2023 | PDF | Code (coming soon) | BibTex

@InProceedings{CLIPFO3D23,
    author    = {Zhang, Junbo and Dong, Runpei and Ma, Kaisheng},
    title     = {CLIP-FO3D: Learning Free Open-World 3D Scene Representations from 2D Dense CLIP},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
    month     = {October},
    year      = {2023},
    pages     = {2048-2059}
}

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
Zekun Qi*, Runpei Dong*, Guofan Fan, Zheng Ge, Xiangyu Zhang, Kaisheng Ma, Li Yi
ICML 2023 | PDF | Code | OpenReview | Slides | BibTex

@InProceedings{ReCon23,
  title = 	 {Contrast with Reconstruct: Contrastive 3{D} Representation Learning Guided by Generative Pretraining},
  author =       {Qi, Zekun and Dong, Runpei and Fan, Guofan and Ge, Zheng and Zhang, Xiangyu and Ma, Kaisheng and Yi, Li},
  booktitle = 	 {Proceedings of the 40th International Conference on Machine Learning},
  pages = 	 {28223--28243},
  year = 	 {2023},
  editor = 	 {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan},
  volume = 	 {202},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {23--29 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v202/qi23a/qi23a.pdf},
  url = 	 {https://proceedings.mlr.press/v202/qi23a.html},
}

Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
Runpei Dong, Zekun Qi, Linfeng Zhang, Junbo Zhang, Jianjian Sun, Zheng Ge, Li Yi, Kaisheng Ma
ICLR 2023 | PDF | Code | OpenReview | Slides | BibTex

@inproceedings{ACT23,
  title={Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?},
  author={Runpei Dong and Zekun Qi and Linfeng Zhang and Junbo Zhang and Jianjian Sun and Zheng Ge and Li Yi and Kaisheng Ma},
  booktitle={The Eleventh International Conference on Learning Representations},
  year={2023},
  url={https://openreview.net/forum?id=8Oun8ZUVe8N}
}

PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection
Linfeng Zhang*, Runpei Dong*, Hung-Shuo Tai, Kaisheng Ma
CVPR 2023 | PDF | Code | BibTex

@InProceedings{PointDistiller23,
    author    = {Zhang, Linfeng and Dong, Runpei and Tai, Hung-Shuo and Ma, Kaisheng},
    title     = {PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2023},
    pages     = {21791-21801}
}

Contrastive Deep Supervision
Linfeng Zhang, Xin Chen, Junbo Zhang, Runpei Dong, Kaisheng Ma
ECCV 2022 | PDF | Code | Slides | BibTex
Oral Presentation (2.7%)

@inproceedings{CDS22,
  author       = {Linfeng Zhang and
                  Xin Chen and
                  Junbo Zhang and
                  Runpei Dong and
                  Kaisheng Ma},
  title        = {Contrastive Deep Supervision},
  booktitle    = {Computer Vision - {ECCV} 2022 - 17th European Conference, Tel Aviv,
                  Israel, October 23-27, 2022, Proceedings, Part {XXVI}},
  series       = {Lecture Notes in Computer Science},
  volume       = {13686},
  pages        = {1--19},
  publisher    = {Springer},
  year         = {2022},
  url          = {https://doi.org/10.1007/978-3-031-19809-0\_1},
  doi          = {10.1007/978-3-031-19809-0\_1}
}

Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks
Runpei Dong*, Zhanhong Tan*, Mengdi Wu, Linfeng Zhang, Kaisheng Ma
ICML 2022 | PDF | Code | Slides | BibTex
Spotlight Presentation

@InProceedings{DGMS22,
  title = 	 {Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks},
  author =       {Dong, Runpei and Tan, Zhanhong and Wu, Mengdi and Zhang, Linfeng and Ma, Kaisheng},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {5343--5359},
  year = 	 {2022},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher = 	 {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/dong22a/dong22a.pdf},
  url = 	 {https://proceedings.mlr.press/v162/dong22a.html},
}