Ye Li (李也)
I am a Ph.D. student at the Information Theory and Machine Learning Group (ITML Group) & Multimedia Laboratory (MMLab@SIGS), Tsinghua Shenzhen International Graduate School, Tsinghua University, where I lead the Efficient Deep Learning and Embodiment Group. I am advised by Prof. Shu-Tao Xia and Prof. Zhi Wang, and co-advised by Prof. Yuan Meng. Previously, I received my Master's degree from Nankai University, where I worked with Prof. Zhongxin Liu on swarm intelligence and learning-based control in the Intelligent Predictive Adaptive Control Lab. I obtained my Bachelor's degree from Nanjing Agricultural University, where I worked on robot perception and control with Prof. Wei Lu in the NJAUROBOT_LAB.
My research interests focus on:
- Embodied Intelligence: building accurate, efficient, and generalizable embodied large models that perceive, reason, and act in the physical world, such as Vision-Language-Action (VLA) models, Diffusion Policies (DP), World Action Models (WAM), etc.
- Efficient Artificial Intelligence: making powerful large models available to everyone under limited compute, such as efficient inference and compression for large language models (LLMs), including token compression, network pruning, quantization, sparsity, caching, etc.
📰 Latest News
- Oct 2026 arXivGUIFlow is released — welcome to discuss! 💬
- Sep 2026 AcceptElegantVLA is accepted by NeurIPS 2026 — see you in Sydney 🇦🇺
- Sep 2026 AcceptTS-DP is accepted by IEEE TMM
- Jun 2026 AcceptRoboStream is accepted by ECCV 2026 — see you in Malmö 🇸🇪
- May 2026 AcceptSAG is accepted by ICML 2026 — see you in Seoul 🇰🇷
- Feb 2026 AcceptTTS & VVS are accepted by CVPR 2026 — see you in Denver 🇺🇸
- Jan 2026 AcceptSP-VLA & BAC are accepted by ICLR 2026 — see you in Rio 🇧🇷
- Oct 2025 AcceptPRANCE is accepted by IEEE TPAMI
📄 Selected Publications
* = first/co-first author · Full list on Google Scholar / Publications page
@article{li2026guiflow,
title={GUIFlow: Temporal Redundancy-Aware Incremental Inference for GUI Agents},
author={Li, Ye and Ding, Haoran and Liu, Huanan and Meng, Yuan and Shen, Yutian and Wang, Yuansong and Ji, Kangye and Cui, Hanyun and Duan, Hongbo and Tang, Chen and others},
journal={arXiv preprint arXiv:2610.34959},
year={2026}
}

@article{li2026elegantvla,
title={ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models},
author={Li, Ye and Liu, Huanan and Ji, Kangye and Meng, Yuan and Fan, Jiajun and Wang, Yuansong and Qin, Shiyu and Wu, Chenglei and Xia, Shu-Tao and Wang, Zhi},
journal={arXiv preprint arXiv:2605.29438},
year={2026}
}

@article{li2025ts,
title={Ts-dp: Reinforcement speculative decoding for temporal adaptive diffusion policy acceleration},
author={Li, Ye and Feng, Jiahe and Meng, Yuan and Ji, Kangye and Tang, Chen and Wen, Xinwan and Xia, Shutao and Wang, Zhi and Zhu, Wenwu},
journal={arXiv preprint arXiv:2512.15773},
year={2025}
}

@article{li2025sp,
title={Sp-vla: A joint model scheduling and token pruning approach for vla model acceleration},
author={Li, Ye and Meng, Yuan and Sun, Zewen and Ji, Kangye and Tang, Chen and Fan, Jiajun and Ma, Xinzhu and Xia, Shutao and Wang, Zhi and Zhu, Wenwu},
journal={arXiv preprint arXiv:2506.12723},
year={2025}
}

@article{li2025prance,
title={Prance: Joint token-optimization and structural channel-pruning for adaptive vit inference},
author={Li, Ye and Tang, Chen and Meng, Yuan and Fan, Jiajun and Chai, Zenghao and Ma, Xinzhu and Wang, Zhi and Zhu, Wenwu},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2025},
publisher={IEEE}
}

@article{li2023ddpg,
title={A DDPG-based solution for optimal consensus of continuous-time linear multi-agent systems},
author={Li, Ye and Liu, ZhongXin and Lan, Ge and Sader, Malika and Chen, ZengQiang},
journal={Science China Technological Sciences},
volume={66},
number={8},
pages={2441--2453},
year={2023},
publisher={Springer}
}

@article{huang2026robostream,
title={RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics},
author={Huang, Yuzhi and Wu, Jie and Bu, Weijue and Xiong, Ziyi and Jiang, Gaoyang and Li, Ye and Ji, Kangye and Xie, Shuzhao and Huang, Yue and Wu, Chenglei and others},
journal={arXiv preprint arXiv:2603.12939},
year={2026}
}

@inproceedings{ji2026sparse,
title={Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning},
author={Ji, Kangye and Zhou, Jianbo and Meng, Yuan and Li, Ye and Cui, Hanyun and Wang, Zhi},
booktitle={Proceedings of the International Conference on Machine Learning},
year={2026}
}

@inproceedings{dong2026vvs,
title={Vvs: Accelerating speculative decoding for visual autoregressive generation via partial verification skipping},
author={Dong, Haotian and Li, Ye and Lu, Rongwei and Tang, Chen and Xia, Shu-Tao and Wang, Zhi},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={12173--12182},
year={2026}
}

@inproceedings{ji2026test,
title={Test-time Sparsity for Extreme Fast Action Diffusion},
author={Ji, Kangye and Meng, Yuan and Zhou, Jianbo and Li, Ye and Tang, Chen and Wang, Zhi},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={9414--9423},
year={2026}
}

🏅 Academic Service
🔍 Conference Reviewer
📬 Contact
Happy to discuss research, internships, or collaborations. Best reached by email.
📧 liye23@mails.tsinghua.edu.cn · 🏛 Tsinghua Shenzhen International Graduate School (SIGS)
CV · 💼 LinkedIn · 🔬 ORCID