publications

2025

1. ICCV’25

   

   Learning Precise Affordances from Egocentric Videos for Robotic Manipulation

   Gen Li, Nikolaos Tsagkas, Jifei Song, Ruaridh Mon-Williams, Sethu Vijayakumar, and 2 more authors

   In IEEE/CVF International Conference on Computer Vision, 2025

   arXiv Bib 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},
   }

2. ICCV’25

   

   Principles of Visual Tokens for Efficient Video Understanding

   Xinyue Hao, Gen Li, Shreyank N Gowda, Robert B Fisher, Jonathan Huang, and 2 more authors

   In IEEE/CVF International Conference on Computer Vision, 2025

   arXiv Bib

   @inproceedings{hao2024principles,
     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},
   }

3. IROS’25

   

   Resource-Efficient Affordance Grounding with Complementary Depth and Semantic Prompts

   Yizhou Huang, Fan Yang, Guoliang Zhu, Gen Li, Hao Shi, and 4 more authors

   In International Conference on Intelligent Robots and Systems, 2025

   arXiv Bib Code

   @inproceedings{huang2025resource,
     title = {Resource-Efficient Affordance Grounding with Complementary Depth and Semantic Prompts},
     author = {Huang, Yizhou and Yang, Fan and Zhu, Guoliang and Li, Gen and Shi, Hao and Zuo, Yukun and Chen, Wenrui and Li, Zhiyong and Yang, Kailun},
     booktitle = {International Conference on Intelligent Robots and Systems},
     year = {2025},
   }

4. 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

   

   @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},
   }

2024

1. ECCVW’24

   

   Watt for what: Rethinking deep learning’s energy-performance relationship

   Shreyank N Gowda, Xinyue Hao, Gen Li, Shashank Narayana Gowda, Xiaobo Jin, and 1 more author

   In European Conference on Computer Vision Workshop, 2024

   Bib PDF

   @inproceedings{gowda2025watt,
     title = {Watt for what: Rethinking deep learning’s energy-performance relationship},
     author = {Gowda, Shreyank N and Hao, Xinyue and Li, Gen and Gowda, Shashank Narayana and Jin, Xiaobo and Sevilla-Lara, Laura},
     booktitle = {European Conference on Computer Vision Workshop},
     pages = {388--405},
     year = {2024},
     organization = {Springer},
   }

2. 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},
   }

2023

1. IJCNN’23

   

   Referenceless User Controllable Semantic Image Synthesis

   Jonghyun Kim, Gen Li, and Joongkyu Kim

   In International Joint Conference on Neural Networks, 2023

   arXiv Bib Code

   @inproceedings{Refer,
     title = {Referenceless User Controllable Semantic Image Synthesis},
     author = {Kim, Jonghyun and Li, Gen and Kim, Joongkyu},
     booktitle = {International Joint Conference on Neural Networks},
     year = {2023},
   }

2. 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},
   }

2021

1. CVPR’21

   

   Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

   Gen Li, Varun Jampani, Laura Sevilla-Lara, Deqing Sun, Jonghyun Kim, and 1 more author

   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},
   }

2. BMVC’21

   

   SuperStyleNet: Deep Image Synthesis with Superpixel Based Style Encoder

   Jonghyun Kim, Gen Li, Cheolkon Jung, and Joongkyu Kim

   In British Machine Vision Conference, 2021

   arXiv Bib Code

   @inproceedings{kim2021superstylenet,
     title = {SuperStyleNet: Deep Image Synthesis with Superpixel Based Style Encoder},
     author = {Kim, Jonghyun and Li, Gen and Jung, Cheolkon and Kim, Joongkyu},
     booktitle = {British Machine Vision Conference},
     year = {2021},
   }

3. PR

   

   Weakly-supervised temporal attention 3D network for human action recognition

   Jonghyun Kim, Gen Li, Inyong Yun, Cheolkon Jung, and Joongkyu Kim

   Pattern Recognition, 2021

   Bib PDF

   @article{KIM2021108068,
     title = {Weakly-supervised temporal attention 3D network for human action recognition},
     journal = {Pattern Recognition},
     volume = {119},
     pages = {108068},
     year = {2021},
     issn = {0031-3203},
     author = {Kim, Jonghyun and Li, Gen and Yun, Inyong and Jung, Cheolkon and Kim, Joongkyu},
     keywords = {Action recognition, Temporal attention, Convolutional neural network, Weakly-supervised learning, Video analysis, Video classification},
   }

4. Neurocom

   

   Edge and identity preserving network for face super-resolution

   Jonghyun Kim, Gen Li, Inyong Yun, Cheolkon Jung, and Joongkyu Kim

   Neurocomputing, 2021

   arXiv Bib PDF Code

   @article{KIM202111,
     title = {Edge and identity preserving network for face super-resolution},
     journal = {Neurocomputing},
     volume = {446},
     pages = {11-22},
     year = {2021},
     issn = {0925-2312},
     author = {Kim, Jonghyun and Li, Gen and Yun, Inyong and Jung, Cheolkon and Kim, Joongkyu},
     keywords = {Super-resolution, Face hallucination, Edge block, Identity loss, Image enhancement},
   }

2020

1. Access

   

   Depth-Wise Asymmetric Bottleneck With Point-Wise Aggregation Decoder for Real-Time Semantic Segmentation in Urban Scenes

   Gen Li, Shenlu Jiang, Inyong Yun, Jonghyun Kim, and Joongkyu Kim

   IEEE Access, 2020

   Bib PDF

   @article{dab_access,
     title = {Depth-Wise Asymmetric Bottleneck With Point-Wise Aggregation Decoder for Real-Time Semantic Segmentation in Urban Scenes},
     author = {Li, Gen and Jiang, Shenlu and Yun, Inyong and Kim, Jonghyun and Kim, Joongkyu},
     journal = {IEEE Access},
     year = {2020},
     volume = {8},
     number = {},
     pages = {27495-27506},
   }

2019

1. BMVC’19

   

   DABNet: Depth-wise asymmetric bottleneck for real-time semantic segmentation

   Gen Li and Joongkyu Kim

   In British Machine Vision Conference, 2019

   arXiv Bib Code

   @inproceedings{DABNet,
     title = {DABNet: Depth-wise asymmetric bottleneck for real-time semantic segmentation},
     author = {Li, Gen and Kim, Joongkyu},
     booktitle = {British Machine Vision Conference},
     year = {2019},
   }