🤖 About Me

• I’m a Scientist working at Agency for Science, Technology and Research (A*STAR) in Singapore.

• My research focuses on perception and planning in embodied AI, aiming to empower autonomous systems with the ability to perceive, understand, and navigate complex 3D environments. I work at the intersection of 3D scene understanding, motion planning, and vision-language model, with the goal of bridging visual perception and intelligent decision-making. I have authored over 20 peer-reviewed papers in leading venues, including TPAMI, CVPR, ICCV, RAL, ICRA and IROS.

• I’m always open to collaboration and in-depth discussions. If you’re interested in my research, feel free to get in touch!

🔥 News

• 2026: One paper was accepted to CVPR, one papers were accepted to ICLR, and one paper was accepted to ICASSP.
• 2025-10: We got the 2nd place in Challenge of Multimodal Robot Learning in InternUtopia and Real World and 1st place in simulation stage at IROS2025.
• 2025: Two papers were accepted to ICCV, and one paper was accepted to CVPR.
• 2024.4: I successfully defended my PhD thesis and began my new role as a Scientist at A*STAR.

📖 Experience

Educations

2019.10 ‑ 2024.4, Doctor
Supervisor: Prof. Dr. Juergen Gall
University of Bonn @ Bonn, Germany

2016.09 ‑ 2019.06, Master
Supervisor: Prof. Dr. Ming-Ming Cheng
Nankai University @ Tianjin, China

2012.09 ‑ 2016.06, Bachlor
Supervisor: Prof. Dr. Hong Cheng
University of Electronic Science and Technology of China @ Chengdu, China

Working Experience

2024.03 ‑ Present, Scientist
Agency for Science, Technology and Research (A*STAR) @ Singapore

2023.07 ‑ 2023.11, Research Intern
Qualcomm AI Research @ Amsterdam, Netherlands

2023.1 ‑ 2023.5, Research Intern
Intel Labs @ Munich, Germany

2018.10 ‑ 2018.12, Visisting Student
Technical University of Munich @ Munich, Germany

2018.5 ‑ 2018.8, Research Intern
Alibaba DAMO Academy @ Beijing, China

2017.6 ‑ 2018.2, Research Intern
UISEE @ Beijing, China

📝 Publications

Preprint

• [arXiv 2026] One Agent to Guide Them All: Empowering MLLMs for Vision-and-Language Navigation via Explicit World Representation [PDF]

  Zerui Li, Hongpei Zheng, Fangguo Zhao, Aidan Chan, Jian Zhou, Sihao Lin, Shijie Li, Qi Wu

• [arXiv 2026] Perception-Aware Multimodal Spatial Reasoning from Monocular Images [PDF]

  Yanchun Cheng, Rundong Wang, Xulei Yang, Alok Prakash, Daniela Rus, Marcelo H Ang Jr, Shijie Li

• [arXiv 2025] SpatialReasoner: Active Perception for Large-Scale 3D Scene Understanding [PDF]

  Hongpei Zheng, Shijie Li, Yanran Li, Hujun Yin

• [arXiv 2025] Thinking Ahead: Foresight Intelligence in MLLMs and World Models [PDF]

  Zhantao Gong, Liaoyuan Fan, Qing Guo, Xun Xu, Xulei Yang, Shijie Li

• [arXiv 2025] MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images [PDF]

  Qirui Wang, Jingyi He, Yining Pan, Si Yong Yeo, Xulei Yang, Shijie Li

• [arXiv 2025] Improving the Generalization of Segmentation Foundation Models via Weakly-Supervised and Unsupervised Adaptation

  Haojie Zhang, Yongyi Su, Nanqing Liu, Shijie Li, Xulei Yang, Xiangyu Yue, Kui Jia, Xun Xu

• [arXiv 2025] DiffPCN: Latent Diffusion Model Based on Multi-view Depth Images for Point Cloud Completion [PDF]

  Zijun Li, Hongyu Yan, Shijie Li, Kunming Luo, Li Lu, Xulei Yang, Weisi Lin

• [arXiv 2025] Multi-View Industrial Anomaly Detection with Epipolar Constrained Cross-View Fusion [PDF]

  Yifan Liu, Xun Xu, Shijie Li, Jingyi Liao, Xulei Yang

2026

• [CVPR 2026] PanDA: Panoptic Domain Adaptation for Multimodal Perception in Autonomous Driving

  Yining Pan, Shijie Li, Yuchen Wu, Xulei Yang, Na Zhao

• [ICLR 2026] Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs [PDF] [code]

  Yongyi Su, Haojie Zhang, Shijie Li, Nanqing Liu, Jingyi Liao, Junyi Pan, Yuan Liu, Xiaofen Xing, Chong Sun, Chen Li, Nancy F. Chen, Shuicheng Yan, Xulei Yang and Xun Xu

• [ICASSP 2026] Sam-Guided Multi-View Fusion for Weakly Supervised 3D Point Cloud Segmentation

  Yuena Qiao, Nanqing Liu, Yongyi Su, Shijie Li, Xulei Yang, Bihan Wen, Nancy Chen, Tianrui Li, Xun Xu

2025

• [ICCV 2025] Global-Aware Monocular Semantic Scene Completion with State Space Models [PDF] [code]

  Shijie Li, Zhongyao Cheng, Rong Li, Shuai Li, Juergen Gall, Xun Xu, Xulei Yang

• [ICCV 2025] Future-Aware Interaction Network For Motion Forecasting [PDF] [code]

  Shijie Li, Xun Xu, Si Yong Yeo, Xulei Yang

• [CVPR 2025] Seeground: See and ground for zero-shot open-vocabulary 3d visual grounding [PDF] [code]

  Rong Li, Shijie Li, Lingdong Kong, Xulei Yang, Junwei Liang

• [WACV 2025] VaLID: Variable-Length Input Diffusion for Novel View Synthesis [PDF]

  Shijie Li, Farhad G. Zanjani, Haitam Ben Yahia, Yuki M. Asano, Juergen Gall, Amirhossein Habibian

• [Neurocomputing] SiFH: Siamese Frequency Harmonization Self-Supervised Learning for Motion Forecasting [PDF]

  Chunyu Liu, Zeyu Liu, Tiechui Yao, Shijie Li

2024

• [CVPRW 2024] Tfnet: Exploiting temporal cues for fast and accurate lidar semantic segmentation [PDF]

  Rong Li, Shijie Li, Xieyuanli Chen, Teli Ma, Juergen Gall, Junwei Liang

2023

• [TPAMI] MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation [PDF] [code]

  Shijie Li, Yazan Abu Farha, Yun Liu, Ming-Ming Cheng, Juergen Gall

• [CCDC 2023] Foresight Social-aware Reinforcement Learning for Robot Navigation [PDF]

  Yanying Zhou, Shijie Li, Jochen Garcke

2022

• [BMVC 2022] Dual Pyramid Generative Adversarial Networks for Semantic Image Synthesis [PDF] [code]

  Shijie Li, Ming-Ming Cheng, Juergen Gall

2021

• [RA-L 2021] Moving object segmentation in 3D LiDAR data: A learning-based approach exploiting sequential data [PDF] [code]

  Xieyuanli Chen, Shijie Li, Benedikt Mersch, Lukas Wiesmann, Juergen Gall, Jens Behley, Cyrill Stachniss

• [RA-L 2021] Multi-scale interaction for real-time lidar data segmentation on an embedded platform [PDF] [code]

  Shijie Li, Xieyuanli Chen, Yun Liu, Dengxin Dai, Cyrill Stachniss, Juergen Gall

• [TNNLS] Rethinking 3-D LiDAR point cloud segmentation [PDF] [code]

  Shijie Li, Yun Liu, Juergen Gall

• [ICCV 2021] Spatial-temporal consistency network for low-latency trajectory forecasting [PDF]

  Shijie Li, Yanying Zhou, Jinhui Yi, Juergen Gall

2020

• [AAAI 2020] MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation [PDF] [code]

  Yu Qiu, Yun Liu, Shijie Li, Jing Xu

• [RA-L 2020]Pose Refinement Graph Convolutional Network for Skeleton-based Action Recognition [PDF] [code]

  Shijie Li, Jinhui Yi, Yazan Abu Farha, Juergen Gall

• [Neurocomputing] Refinedbox: Refining for fewer and high-quality object proposals [PDF]

  Yun Liu, Shijie Li, Ming-Ming Cheng

2019

• [Frontiers of Computer Science] Joint salient object detection and existence prediction [PDF]

  Huaizu Jiang, Ming-Ming Cheng, Shijie Li, Ali Borji, Jingdong Wang

2018

• [IJCAI 2018] Del: Deep embedding learning for efficient image segmentation [PDF] [code]

  Yun Liu, Peng-Tao Jiang, Vahan Petrosyan, Shijie Li, Jiawang Bian, Le Zhang, Ming-Ming Cheng

• [ICRA 2018] Direct line guidance odometry [PDF]

  Shijie Li, Bo Ren, Yun Liu, Ming-Ming Cheng, Duncan Frost, Victor Adrian Prisacariu

• [IROS 2018] Structured skip list: A compact data structure for 3D reconstruction [PDF]

  Shijie Li, Ming-Ming Cheng, Yun Liu, Shao-Ping Lu, YaHui Wang, Victor Adrian Prisacariu

🌏 Misc.

I enjoy exploring different places—here’s a list of countries I’ve visited so far 😊

• Asia: 🇨🇳 🇸🇬 🇲🇾 🇮🇩 🇶🇦 🇦🇪 🇰🇷

• Europe: 🇸🇪 🇵🇱 🇬🇧 🇨🇿 🇦🇹 🇮🇹 🇲🇨 🇫🇷 🇵🇹 🇪🇸 🇨🇭 🇧🇪 🇩🇪 🇳🇱 🇱🇺

• North America: 🇺🇸

• Oceania: 🇦🇺