Gen Li

@article{affordance-survey,
  title = {From Passive Perception to Active Interaction: A Survey of Affordance Learning for Embodied AI},
  author = {Li, Gen and Wang, Hanqing and Li, Jingliang and Han, Yifan and Jia, Jindou and Lin, Tao and Liu, Yuanzhe and Wang, Yutong and Zhao, Bo and Ding, Fangqiang and Nguyen, Anh and Sevilla-Lara, Laura and Xu, Huazhe and Chirikjian, Gregory S. and Pollefeys, Marc and Mees, Oier and Xiong, Hui and Yang, Jianfei},
  year = {2026},
  journal = {Preprints.org},
}

@article{mmhri,
  title = {mmHRI: Towards Privacy-Preserving Human-Robot Interaction with Millimeter-Wave Radar},
  author = {Fan, Junqiao and Hu, Yuxuan and Lyu, Bofan and Lu, Yanshuo and Liu, Pengfei and Zhang, Jiarui and Ding, Fangqiang and Xie, Lihua and Li, Gen and Yang, Jianfei},
  year = {2026},
  journal = {arXiv},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@inproceedings{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},
  booktitle = {Conference on Neural Information Processing Systems},
}

@inproceedings{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},
  booktitle = {Conference on Neural Information Processing Systems},
}

@inproceedings{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},
  booktitle = {Conference on Neural Information Processing Systems},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}