I am a Ph.D. candidate at Hunan University, expecting to graduate in November 2025 and currently seeking a faculty or postdoctoral position. My research focuses on 3D vision and embodied intelligence, with emphasis on 3D object detection, 3D scene question answering, and automated annotation. I have authored over twenty peer-reviewed publications and serve as a regular reviewer for CVPR, ICCV, ICLR, NeurIPS, and AAAI, as well as IJCV, IEEE Transactions on Mechatronics, IEEE Transactions on Cybernetics, and Expert Systems with Applications.

Email: [email protected]

• 3D vision
• 3D Object detection
• 3D QA
• Embodied Intelligence

1. Zechuan Li, Yu H, Yang Z, et al. AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via Transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023: 1012–1021. (CCF-A, CVPR 2023)

2. Zechuan Li, Yu H, Niu Zhang, et al. GO-N3RDet: Geometry Optimized NeRF-enhanced 3D Object Detector. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025: 27211–27221. (CCF-A, CVPR 2025)

3. Zechuan Li, Hongshan Yu, Yihao Ding, Yan Li, Yong He, Naveed Akhtar. Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering. Information Fusion, Volume 126, Part B, 2026, 126:103624. (JCR Q1; IF: 15.6)

4. Zechuan Li, Hongshan Yu, Yihao Ding, Shuai Yuan, Naveed Akhtar. LPL3D: LVLM-driven Pseudo-Labeling for 3D Object Detection. IEEE Transactions on Circuits and Systems for Video Technology(T-CSVT), 2025. (Accepted; JCR Q1; IF: 11.1)

5. Yan Li, Tianyi Zhang, Zechuan Li, Soyeon Caren Han. A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI). Conference on Empirical Methods in Natural Language Processing.2025.(CCF-B, EMNLP2025).

6. Tongjia Chen, Hongshan Yu, Zhengeng Yang, Zechuan Li, Wei Sun, Chen Chen. OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024: 18888–18898. (CVPR 2024)

7. Jingwen Wang, Hongshan Yu, Xuefei Lin, Zechuan Li, Wei Sun, Naveed Akhtar. EFRNet-VL: An End-to-End Feature Refinement Network for Monocular Visual Localization in Dynamic Environments. Expert Systems with Applications, 243: 122755, 2024. (IF: 7.5)

8. Yanmei Zou, Hongshan Yu, Zhengeng Yang, Zechuan Li, Naveed Akhtar. Improved MLP Point Cloud Processing with High-Dimensional Positional Encoding. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 38(7): 7891–7899, 2024. (AAAI 2024)

9. Shuai Yuan, Hanlin Qin, Renke Kou, Xiang Yan, Zechuan Li, Chenxu Peng, Dongliang Wu. Beyond Full Labels: Energy-Double-Guided Single-Point Prompt for Infrared Small Target Label Generation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025.

10. Chen, Tom Tongjia, Hongshan Yu, Zhengeng Yang, Ming Li, Zechuan Li, Jingwen Wang, Wei Miao, Wei Sun, and Chen Chen. First place solution to the cvpr'2023 aqtc challenge: A function-interaction centric approach with spatiotemporal visual-language alignment. arXiv preprint arXiv:2306.13380 (2023).

• Conferences：CVPR、ICCV、ICLR、NeurIPS、AAAI, etc.
• Journals：IJCV、IEEE Transactions on Image Processing、IEEE Transactions on Mechatronics、IEEE Transactions on Cybernetics、Expert Systems with Applications, etc.