Gen Li

Full Professor @ HNU

Email: ligen [at] g.skku.edu

李根，拟入职湖南大学人工智能与机器人学院教授、博士生导师、国家级高层次青年人才。致力于构建可靠、高效、以人为本的具身智能系统，使机器人能够在复杂物理环境中实现感知、推理与自主行动。研究方向包括机器人学习、多模态基础模型、高效人工智能及人机交互等。

曾任新加坡南洋理工大学担任博士后研究员，合作导师为杨剑飞。博士毕业于英国爱丁堡大学，师从 Laura Sevilla，并由 Timothy Hospedales 教授共同指导。

📢 长期招收博士生、硕士生、博士后、科研助理/实习生及访问学者。欢迎对具身智能、机器人学习及多模态人工智能感兴趣的同学通过邮件联系！

动态

Sep 2026	🎉 UCA-Flow and ADAPT are accepted to CoRL 2026!
Aug 2026	🎉 PhyFilter is accepted by Nature Portfolio Robotics!
Aug 2026	🎉 World Model for Robot Learning: A Comprehensive Survey is accepted by IJRR!
May 2026	🚩 Our latest survey, World Model for Robot Learning, is now out on arXiv!
Apr 2026	🎉 A2A Flow Matching is accepted to RSS 2026!
Mar 2026	📖 Invited to serve as an Area Chair for NeurIPS 2026.
Feb 2026	🎉 Evo-1 and PALM are accepted to CVPR 2026!
Feb 2026	📖 Invited to serve as an Area Chair for BMVC 2026.

代表论文

*/† 表示共同贡献/共同指导完整论文列表请见 Google Scholar

npj Robotics

Physics Filtering Favors the Generalization of Robot Learning

Jindou Jia, Shixuan Han, Meng Wang, Gen Li, Zihan Yang, Sicheng Zhou, Kexin Guo, Jianfei Yang, Xiang Yu, Wei Wang, and Lei Guo

npj Robotics, 2026

arXiv Bib Code Website

@article{phyfilter,
  title = {Physics Filtering Favors the Generalization of Robot Learning},
  author = {Jia, Jindou and Han, Shixuan and Wang, Meng and Li, Gen and Yang, Zihan and Zhou, Sicheng and Guo, Kexin and Yang, Jianfei and Yu, Xiang and Wang, Wei and Guo, Lei},
  year = {2026},
  journal = {npj Robotics},
}

CoRL’26

Unified Condition-Action Modeling for Accurate One-Step Action Generation

Xinyu Zhou, Zikun Cai, Kuangji Zuo, Gen Li, Boyu Ma, Yanshuo Lu, Yutong Song, Mingqi Yuan, Jiayu Chen, and Jianfei Yang

In Conference on Robot Learning, 2026

arXiv Bib Website

@inproceedings{uca-flow,
  title = {Unified Condition-Action Modeling for Accurate One-Step Action Generation},
  author = {Zhou, Xinyu and Cai, Zikun and Zuo, Kuangji and Li, Gen and Ma, Boyu and Lu, Yanshuo and Song, Yutong and Yuan, Mingqi and Chen, Jiayu and Yang, Jianfei},
  year = {2026},
  booktitle = {Conference on Robot Learning},
}

Preprint

ω-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation

Zhe Li, Zhenzhe Zhang, Yangyang Wei, Wenjie Zhang, Xichen Yuan, Peiyuan Zhi, Gen Li, Xinying Guo, Fengjie Gao, Jianfei Yang, and Shanghang Zhang

arXiv, 2026

arXiv Bib Website

@article{omega0,
  title = {ω-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation},
  author = {Li, Zhe and Zhang, Zhenzhe and Wei, Yangyang and Zhang, Wenjie and Yuan, Xichen and Zhi, Peiyuan and Li, Gen and Guo, Xinying and Gao, Fengjie and Yang, Jianfei and Zhang, Shanghang},
  year = {2026},
  journal = {arXiv},
}

Preprint

LA4VLA: Learning to Act without Seeing via Language-Action Pretraining

Tao Lin, Yuxin Du, Yiran Mao, Zewei Ye, Yilei Zhong, Bing Cheng, Yiming Wang, Jiting Liu, Yang Tian, Junchi Yan, Feiran Wu, Zenan Meng, Hu Wei, Yuqian Fu^†, Gen Li^†, and Bo Zhao^†

arXiv, 2026

arXiv Bib Code

@article{la4vla,
  title = {LA4VLA: Learning to Act without Seeing via Language-Action Pretraining},
  author = {Lin, Tao and Du, Yuxin and Mao, Yiran and Ye, Zewei and Zhong, Yilei and Cheng, Bing and Wang, Yiming and Liu, Jiting and Tian, Yang and Yan, Junchi and Wu, Feiran and Meng, Zenan and Wei, Hu and Fu, Yuqian and Li, Gen and Zhao, Bo},
  year = {2026},
  journal = {arXiv},
}

CoRL’26

ADAPT: Analytical Disturbance-Aware Policy Training for Humanoid Locomotion

Bofan Lyu, Jindou Jia, Kuangji Zuo, Yanshuo Lu, Shijia Han, Gen Li, Boyu Ma, Jingliang Li, Geng Li, and Jianfei Yang^†

Conference on Robot Learning, 2026

arXiv Bib Code Website

@article{adapt,
  title = {ADAPT: Analytical Disturbance-Aware Policy Training for Humanoid Locomotion},
  author = {Lyu, Bofan and Jia, Jindou and Zuo, Kuangji and Lu, Yanshuo and Han, Shijia and Li, Gen and Ma, Boyu and Li, Jingliang and Li, Geng and Yang, Jianfei},
  year = {2026},
  journal = {Conference on Robot Learning},
}

Preprint

GIVE: Grounding Human Gestures in Vision-Language-Action Models

Pengfei Liu^*, Gen Li^*, Junqiao Fan, Boyu Ma, Jindou Jia, Yang Xiao, and Jianfei Yang

arXiv, 2026

arXiv Bib Website

@article{give,
  title = {GIVE: Grounding Human Gestures in Vision-Language-Action Models},
  author = {Liu, Pengfei and Li, Gen and Fan, Junqiao and Ma, Boyu and Jia, Jindou and Xiao, Yang and Yang, Jianfei},
  year = {2026},
  journal = {arXiv},
}

Preprint

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning

Geng Li, Guohao Chen, Ting Chen, Shilin Shan, Kuangji Zuo, Bofan Lyu, Tuo An, Gen Li^†, and Jianfei Yang^†

arXiv, 2026

arXiv Bib

@article{occamtoken,
  title = {OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning},
  author = {Li, Geng and Chen, Guohao and Chen, Ting and Shan, Shilin and Zuo, Kuangji and Lyu, Bofan and An, Tuo and Li, Gen and Yang, Jianfei},
  year = {2026},
  journal = {arXiv},
}

Preprint

MARS Policy: Multimodality Only When It Matters

Jindou Jia, Tuo An, Yuxuan Hu, Gen Li, Jingliang Li, Bohan Hou, Xiangyu Chen, Jiaqi Bai, Bofan Lyu, and Jianfei Yang

arXiv, 2026

arXiv Bib Website

@article{mars-policy,
  title = {MARS Policy: Multimodality Only When It Matters},
  author = {Jia, Jindou and An, Tuo and Hu, Yuxuan and Li, Gen and Li, Jingliang and Hou, Bohan and Chen, Xiangyu and Bai, Jiaqi and Lyu, Bofan and Yang, Jianfei},
  year = {2026},
  journal = {arXiv},
}

Preprint

Gaze2Act: Gaze-Conditioned Vision-Language-Action Policies for Interactive Robot Manipulation

Kuangji Zuo^*, Gen Li^*, Bofan Lyu, Yanshuo Lu, Boyu Ma, Shijia Han, Xinyu Zhou, Xichen Yuan, Chuhao Zhou, Jiaqi Bai, Geng Li, and Jianfei Yang

arXiv, 2026

arXiv Bib Website

@article{gaze2act,
  title = {Gaze2Act: Gaze-Conditioned Vision-Language-Action Policies for Interactive Robot Manipulation},
  author = {Zuo, Kuangji and Li, Gen and Lyu, Bofan and Lu, Yanshuo and Ma, Boyu and Han, Shijia and Zhou, Xinyu and Yuan, Xichen and Zhou, Chuhao and Bai, Jiaqi and Li, Geng and Yang, Jianfei},
  year = {2026},
  journal = {arXiv},
}

Preprint

Feedback World Model Enables Precise Guidance of Diffusion Policy

Tuo An, Jindou Jia, Gen Li, Jingliang Li, Chuhao Zhou, Pengfei Liu, Bofan Lyu, Jiaqi Bai, Xinying Guo, Geng Li, and Jianfei Yang

arXiv, 2026

arXiv Bib Website

@article{feedback-wm,
  title = {Feedback World Model Enables Precise Guidance of Diffusion Policy},
  author = {An, Tuo and Jia, Jindou and Li, Gen and Li, Jingliang and Zhou, Chuhao and Liu, Pengfei and Lyu, Bofan and Bai, Jiaqi and Guo, Xinying and Li, Geng and Yang, Jianfei},
  year = {2026},
  journal = {arXiv},
}

Preprint

FLASH: Efficient Visuomotor Policy via Sparse Sampling

Jiaqi Bai, Jindou Jia, Yuxuan Hu, Gen Li, Xiangyu Chen, Tuo An, Kuangji Zuo, and Jianfei Yang

arXiv, 2026

arXiv Bib Website

@article{flash,
  title = {FLASH: Efficient Visuomotor Policy via Sparse Sampling},
  author = {Bai, Jiaqi and Jia, Jindou and Hu, Yuxuan and Li, Gen and Chen, Xiangyu and An, Tuo and Zuo, Kuangji and Yang, Jianfei},
  year = {2026},
  journal = {arXiv},
}

Preprint

Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model

Tao Lin, Yuxin Du, Jiting Liu, Nuobei Zhu, Yunhe Li, Yuqian Fu, Yinxinyu Chen, Hongyi Cai, Zewei Ye, Bing Cheng, Kai Ye, Yiran Mao, Yilei Zhong, MingKang Dong, Junchi Yan, Gen Li^†, and Bo Zhao^†

arXiv, 2026

arXiv Bib Code

@article{evo-depth,
  title = {Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model},
  author = {Lin, Tao and Du, Yuxin and Liu, Jiting and Zhu, Nuobei and Li, Yunhe and Fu, Yuqian and Chen, Yinxinyu and Cai, Hongyi and Ye, Zewei and Cheng, Bing and Ye, Kai and Mao, Yiran and Zhong, Yilei and Dong, MingKang and Yan, Junchi and Li, Gen and Zhao, Bo},
  year = {2026},
  journal = {arXiv},
}

IJRR

World Model for Robot Learning: A Comprehensive Survey

Bohan Hou^*, Gen Li^*, Jindou Jia^*, Tuo An^*, Xinying Guo^*, Sicong Leng, Haoran Geng, Yanjie Ze, Tatsuya Harada, Philip Torr, Oier Mees, Marc Pollefeys, Zhuang Liu, Jiajun Wu, Pieter Abbeel, Jitendra Malik, Yilun Du, and Jianfei Yang

International Journal of Robotics Research, 2026

arXiv Bib Code Website

@article{wm-survey,
  title = {World Model for Robot Learning: A Comprehensive Survey},
  author = {Hou, Bohan and Li, Gen and Jia, Jindou and An, Tuo and Guo, Xinying and Leng, Sicong and Geng, Haoran and Ze, Yanjie and Harada, Tatsuya and Torr, Philip and Mees, Oier and Pollefeys, Marc and Liu, Zhuang and Wu, Jiajun and Abbeel, Pieter and Malik, Jitendra and Du, Yilun and Yang, Jianfei},
  year = {2026},
  journal = {International Journal of Robotics Research},
}

Preprint

CompassAD: Intent-Driven 3D Affordance Grounding in Functionally Competing Objects

Jingliang Li, Jindou Jia, Tuo An, Chuhao Zhou, Xiangyu Chen, Shilin Shan, Boyu Ma, Bofan Lyu, Gen Li^†, and Jianfei Yang^†

arXiv, 2026

arXiv Bib Code Website

@article{compassad,
  title = {CompassAD: Intent-Driven 3D Affordance Grounding in Functionally Competing Objects},
  author = {Li, Jingliang and Jia, Jindou and An, Tuo and Zhou, Chuhao and Chen, Xiangyu and Shan, Shilin and Ma, Boyu and Lyu, Bofan and Li, Gen and Yang, Jianfei},
  year = {2026},
  journal = {arXiv},
}

Preprint

RoboForge: Physically Optimized Text-Guided Whole-Body Locomotion for Humanoids

Xichen Yuan, Zhe Li, Bofan Lyu, Kuangji Zuo, Yanshuo Lu, Gen Li, and Jianfei Yang

arXiv, 2026

arXiv Bib Website

@article{roboforge,
  title = {RoboForge: Physically Optimized Text-Guided Whole-Body Locomotion for Humanoids},
  author = {Yuan, Xichen and Li, Zhe and Lyu, Bofan and Zuo, Kuangji and Lu, Yanshuo and Li, Gen and Yang, Jianfei},
  year = {2026},
  journal = {arXiv},
}

RSS’26

Action-to-Action Flow Matching

Jindou Jia^*, Gen Li^*, Xiangyu Chen, Tuo An, Yuxuan Hu, Jingliang Li, Xinying Guo, and Jianfei Yang

In Robotics: Science and Systems, 2026

arXiv Bib Code Website

@inproceedings{a2a,
  title = {Action-to-Action Flow Matching},
  author = {Jia, Jindou and Li, Gen and Chen, Xiangyu and An, Tuo and Hu, Yuxuan and Li, Jingliang and Guo, Xinying and Yang, Jianfei},
  year = {2026},
  booktitle = {Robotics: Science and Systems},
}

CVPR’26

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

Tao Lin, Yilei Zhong, Yuxin Du, Jingjing Zhang, Jiting Liu, Yinxinyu Chen, Encheng Gu, Ziyan Liu, Hongyi Cai, Yanwen Zou, Lixing Zou, Zhaoye Zhou, Gen Li^†, and Bo Zhao^†

In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

arXiv Bib Code Website

@inproceedings{evo1,
  title = {Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment},
  author = {Lin, Tao and Zhong, Yilei and Du, Yuxin and Zhang, Jingjing and Liu, Jiting and Chen, Yinxinyu and Gu, Encheng and Liu, Ziyan and Cai, Hongyi and Zou, Yanwen and Zou, Lixing and Zhou, Zhaoye and Li, Gen and Zhao, Bo},
  year = {2026},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
}

CVPR’26

PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation

Yuanzhe Liu, Jingyuan Zhu, Yuchen Mo, Gen Li, Xu Cao, Jin Jin, Yifan Shen, Zhengyuan Li, Tianjiao Yu, Wenzhen Yuan, Fangqiang Ding, and Ismini Lourentzou

In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

arXiv Bib

@inproceedings{palm,
  title = {PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation},
  author = {Liu, Yuanzhe and Zhu, Jingyuan and Mo, Yuchen and Li, Gen and Cao, Xu and Jin, Jin and Shen, Yifan and Li, Zhengyuan and Yu, Tianjiao and Yuan, Wenzhen and Ding, Fangqiang and Lourentzou, Ismini},
  year = {2026},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
}

Preprint

Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding

Tao Lin^*, Gen Li^*, Yilei Zhong, Yanwen Zou, Yuxin Du, Jiting Liu, Encheng Gu, and Bo Zhao

arXiv, 2026

arXiv Bib Code Website

@article{evo0,
  title = {Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding},
  author = {Lin, Tao and Li, Gen and Zhong, Yilei and Zou, Yanwen and Du, Yuxin and Liu, Jiting and Gu, Encheng and Zhao, Bo},
  year = {2026},
  journal = {arXiv},
}

AAAI’26

Mask2IV: Interaction-Centric Video Generation via Mask Trajectories

Gen Li, Bo Zhao, Jianfei Yang, and Laura Sevilla-Lara

In AAAI Conference on Artificial Intelligence, 2026

arXiv Bib Code Website

@inproceedings{Mask2IV,
  title = {Mask2IV: Interaction-Centric Video Generation via Mask Trajectories},
  author = {Li, Gen and Zhao, Bo and Yang, Jianfei and Sevilla-Lara, Laura},
  year = {2026},
  booktitle = {AAAI Conference on Artificial Intelligence},
}

ICCV’25

Learning Precise Affordances from Egocentric Videos for Robotic Manipulation

Gen Li, Nikolaos Tsagkas, Jifei Song, Ruaridh Mon-Williams, Sethu Vijayakumar, Kun Shao, and Laura Sevilla-Lara

In IEEE/CVF International Conference on Computer Vision, 2025

arXiv Bib Code Website

@inproceedings{Aff-Grasp,
  title = {Learning Precise Affordances from Egocentric Videos for Robotic Manipulation},
  author = {Li, Gen and Tsagkas, Nikolaos and Song, Jifei and Mon-Williams, Ruaridh and Vijayakumar, Sethu and Shao, Kun and Sevilla-Lara, Laura},
  year = {2025},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
}

ICCV’25

Principles of Visual Tokens for Efficient Video Understanding

Xinyue Hao, Gen Li, Shreyank N Gowda, Robert B Fisher, Jonathan Huang, Anurag Arnab, and Laura Sevilla-Lara

In IEEE/CVF International Conference on Computer Vision, 2025

arXiv Bib

@inproceedings{LITE,
  title = {Principles of Visual Tokens for Efficient Video Understanding},
  author = {Hao, Xinyue and Li, Gen and Gowda, Shreyank N and Fisher, Robert B and Huang, Jonathan and Arnab, Anurag and Sevilla-Lara, Laura},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year = {2025},
}

NMI

Embodied Large Language Models Enable Robots to Complete Complex Tasks in Unpredictable Environments

Ruaridh Mon-Williams^†, Gen Li^†, Ran Long, Wenqian Du, and Chris Lucas

Nature Machine Intelligence, 2025

Bib PDF Video Code

@article{ELLMER,
  title = {Embodied Large Language Models Enable Robots to Complete Complex Tasks in Unpredictable Environments},
  author = {Mon-Williams, Ruaridh and Li, Gen and Long, Ran and Du, Wenqian and Lucas, Chris},
  journal = {Nature Machine Intelligence},
  year = {2025},
}

CVPR’24

One-Shot Open Affordance Learning with Foundation Models

Gen Li, Deqing Sun, Laura Sevilla-Lara, and Varun Jampani

In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

arXiv Bib Code Website

@inproceedings{OOAL,
  title = {One-Shot Open Affordance Learning with Foundation Models},
  author = {Li, Gen and Sun, Deqing and Sevilla-Lara, Laura and Jampani, Varun},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2024},
}

CVPR’23

LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding

Gen Li, Varun Jampani, Deqing Sun, and Laura Sevilla-Lara

In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

arXiv Bib Code Website

@inproceedings{LOCATE,
  title = {LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding},
  author = {Li, Gen and Jampani, Varun and Sun, Deqing and Sevilla-Lara, Laura},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2023},
}

CVPR’21

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

Gen Li, Varun Jampani, Laura Sevilla-Lara, Deqing Sun, Jonghyun Kim, and Joongkyu Kim

In IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021

arXiv Bib Code Website

@inproceedings{ASGNet,
  title = {Adaptive Prototype Learning and Allocation for Few-Shot Segmentation},
  author = {Li, Gen and Jampani, Varun and Sevilla-Lara, Laura and Sun, Deqing and Kim, Jonghyun and Kim, Joongkyu},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {8334--8343},
  year = {2021},
}

学术服务

领域主席: NeurIPS 2026, BMVC 2026
期刊审稿人: Nature Machine Intelligence, Nature Reviews Computing, TIP, etc.
会议审稿人: CVPR, ICCV, ECCV, NeurIPS, ICLR, RSS, CoRL, ICRA, IROS, AAAI, etc.