黎向阳  副研究员  

研究方向:

所属部门:智能信息处理重点实验室

导师类别:

联系方式:lixiangyang@ict.ac.cn

个人网页:https://lixyresearch.github.io

简       历:

黎向阳,中国科学院计算技术研究所副研究员,CAAI具身智能专委会首届委员,CAAI智能服务专委会委员。聚焦动态环境下视觉语言多模态关联理解与具身导航,在视觉语言多模态预训练、视觉语言具身导航,多模态定位检测等方面展开系列研究,先后获新一代人工智能国家科技重大专项子课题、国家自然科学基金青年项目、博士后创新人才支持计划等资助。

教育及工作经历:

2026年10月 — 今:中国科学院计算技术研究所,副研究员

2023年8月 — 2026年10月:中国科学院计算技术研究所,助理研究员

2020年10月 — 2023年7月:中国科学院计算技术研究所,特别研究助理(博士后)

2015年9月 — 2020年9月:中国科学院计算技术研究所(中国科学院大学),博士生

2012年9月 — 2015年7月:首都师范大学,信息工程学院,硕士生

2008年9月 — 2012年7月:武汉工程大学,计算机科学与工程学院,本科生

主要论著:

论文完整列表请参见:

https://scholar.google.com/citations?user=n6WBCgUAAAAJ&hl

[1] Jiahao Yang, Zihan Wang, Xiangyang Li, Xing Zhu, Yujun Shen, Yinghao Xu, Shuqiang Jiang. GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 40053-40063, 2026.

[2] Pengfei Zhou, Weiqing Min, Chaoran Fu, Ying Jin, Mingyu Huang, Xiangyang Li, Shuhuan Mei, Shuqiang Jiang. FoodSky: A food-oriented large language model that can pass the chef and dietetic examinations. Patterns, vol. 6, no. 5, 2025.

[3] Zihan Wang, Xiangyang Li, Jiahao Yang, Yeqi Liu, Junjie Hu, Ming Jiang, Shuqiang Jiang. Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13753-13762, 2024.

[4] Zihan Wang, Xiangyang Li, Jiahao Yang, Yeqi Liu, Shuqiang Jiang. Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation. In Proceedings of the Conference on Robot Learning (CoRL), pp. 2982-2995, 2024.

[5] Xiangyang Li, Zihan Wang, Jiahao Yang, Yaowei Wang, Shuqiang Jiang. KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2583-2592, 2023.

[6] Yongqing Zhu, Xiangyang Li, Mao Zheng, Jiahao Yang, Zihan Wang, Xiaoqian Guo, Zifeng Chai, Yuchen Yuan, Shuqiang Jiang. Focus and Align: Learning Tube Tokens for Video-Language Pre-training. IEEE Transactions on Multimedia (IEEE TMM), vol. 25, pp. 8036-8050, 2023.

[7] Zihan Wang, Xiangyang Li, Jiahao Yang, Yeqi Liu, Shuqiang Jiang. GridMM: Grid Memory Map for Vision-and-Language Navigation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 15625-15636, 2023.

[8] Jiahao Yang, Xiangyang Li, Mao Zheng, Zihan Wang, Yongqing Zhu, Xiaoqian Guo, Yuchen Yuan, Zifeng Chai, Shuqiang Jiang. MemBridge: Video-Language Pre-training with Memory-Augmented Inter-Modality Bridge. IEEE Transactions on Image Processing (IEEE TIP), vol. 32, pp. 4073-4087, 2023.

[9] Xiaoqian Guo, Xiangyang Li, Yaowei Wang, Shuqiang Jiang. TransWeaver: Weave Image Pairs for Class Agnostic Common Object Detection. IEEE Transactions on Image Processing (IEEE TIP), vol. 32, pp. 2947-2959, 2023.

[10] Shuqiang Jiang, Yaohui Zhu, Chenlong Liu, Xinhang Song, Xiangyang Li, Weiqing Min. Dataset Bias in Few-shot Image Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), vol. 45, no. 1, pp. 229-246, 2023.

[11] Xiangyang Li, Luis Herranz, Shuqiang Jiang. Multifaceted Analysis of Fine-Tuning in Deep Model for Visual Recognition. ACM Transactions on Data Science (ACM TDS), vol. 1, no. 1, pp. 4:1-4:22, 2020.

[12] Xiaoqian Guo, Xiangyang Li, Shuqiang Jiang. Expressional Region Retrieval. In Proceedings of the 28rd ACM International Conference on Multimedia (ACM MM), pp. 2581–2589, 2020.

[13] Xiangyang Li, Shuqiang Jiang. Know More Say Less: Image Captioning Based on Scene Graphs. IEEE Transactions on Multimedia (IEEE TMM), vol. 21, no. 8, pp. 2117-2130, 2019.

[14] Xiangyang Li, Shuqiang Jiang, Jungong Han. Learning Object Context for Dense Captioning. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), pp. 8650-8657, 2019.

[15] Shuqiang Jiang, Sisi Liang, Chengpeng Chen, Yaohui Zhu, Xiangyang Li. Class Agnostic Image Common Object Detection. IEEE Transactions on Image Processing (IEEE TIP), vol. 28, no. 6, pp. 2836-2846, 2019.

[16] Xiangyang Li, Shuqiang Jiang. Bundled Object Context for Referring Expressions. IEEE Transactions on Multimedia (IEEE TMM), vol. 20, no. 10, pp. 2749-2760, 2018.

[17] Xiangyang Li, Xinhang Song, Luis Herranz, Yaohui Zhu, Shuqiang Jiang. Image Captioning with Both Object and Scene Information. In Proceedings of the 24rd ACM International Conference on Multimedia (ACM MM), pp. 1107-1110, 2016.

[18] Luis Herranz, Shuqiang Jiang, Xiangyang Li. Scene Recognition with CNNs: Objects, Scales and Dataset Bias. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 571-579, 2016.

科研项目:

[1] 新一代人工智能国家科技重大专项子课题:面向智能制造与建造的具身智能体系统,项目负责人;

[2] 国家自然科学基金青年科学基金C类:视觉语言关联区域的定位与描述方法研究,项目负责人;

[3] 博士后创新人才支持计划:面向多模态交互的图像内容语言描述与理解技术研究,项目负责人;

[4] 中国科学院特别研究助理资助项目:图像内容语言描述与理解,项目负责人;

[5] 科技创新2030-“新一代人工智能”重大项目课题:人类直觉、知识经验与情境行为的混合学习方法,主要参与人;

[6] 国家自然科学基金重大项目课题:作业行为驱动的实时定位与动态路径规划,主要参与人;

[7] 国家自然科学基金联合基金重点支持项目:野外环境下多模态融合的地面无人平台跨场景智能感知,主要参与人;

[8] 国家自然科学基面上项目:小数据驱动的视觉识别认知模型关键技术研究,主要参与人。

获奖及荣誉:

2025年中国科学院计算技术研究所优秀研究人员

2025年CVPR Embodied AI动态环境中具身决策冠军

2023年CVPR Embodied AI 视觉语言导航RxR Habitat竞赛冠军

2020年中国科学院院长优秀奖