Qian Zheng 郑乾

Assistant Professor

College of Computer Science and Technology,
Zhejiang University, Hangzhou, China.
Email: qianzheng@zju.edu.cn
Official Academic Profile: [En][中文]
[Google Scholar] [News] [Publications] [Activities] [Teaching]

I am a Tenure-Track Assistant Professor (ZJU 100-Young Professor, 百人计划研究员) at Zhejiang University, working closely with Prof Gang Pan and Prof Huajin Tang. I obtained my PhD (2017) and BEng (2011) from ZJU under Prof Gang Pan's supervision. Previously, I was a Research Fellow at the ROSE Lab, Nanyang Technological University (2018–2022), collaborating with Prof Boxin Shi, Prof Xudong Jiang, and Prof Alex Kot.

My research dedicated to bridging brain-inspired computing and mainstream AI. We have proved that neuromorphic models can match or outperform conventional deep learning across diverse scales—from Large Language Models (ACL'26) and EEG Foundation Models (AAAI'26) to 3D Neural Rendering (AAAI'24, CVPR'26). Moving forward, my group focuses on hardware-software co-design to co-optimize neuromorphic algorithms with specialized hardware.







		👉 常年招收：博士后、博士、硕士、本科实习生，欢迎邮件联系。组内具有充足科研经费，提供每周一对一科研指导，为个人发展与规划提供建议或帮助。希望你：目标长远不短视、刻苦勤奋不摆烂、态度端正能抗压、乐观积极易沟通。原则上需要提前进组互相熟悉，最好是暑期线下过来。如果三天内我没邮件回复，代表我没有相应的博士硕士指标、或没有合适的科研项目。

🔥 News [Click to Expand]

📚 Selected Works Since 2023 [SNs and SNNs] [Event Camera based CV]

Spiking Neurons (SNs) and Spiking Neural Networks (SNNs)

	SPEAK: Spiking Neurons as an Entropy-Aware Tokenizer for Large Language Models Ming Chen, Wenyao Li, Chao Liang, Shi Gu, Peng Lin, De Ma, Huajin Tang, Qian Zheng, Gang Pan Proceedings of the Association for Computational Linguistics (ACL), Jul 2026 [paper][code] Leverage the unique reset machanism from SN to model historical tokenization in LLM
	Dynamic-Static Decomposition for Novel View Synthesis of Dynamic Scenes with Spiking Neurons Lingyun Dai^#, Zehao Chen^#, Yan Liu, Shi Gu, Peng Lin, De Ma, Huajin Tang, Qian Zheng, Gang Pan The IEEE/CVF Conference on Computer Vision and Pattern Recognition* (CVPR), Jun 2026 [Project] A discontinuous dynamic–static tagging field based on the SNs, reducing uncertainty-induced misclassification near object boundaries
	Robust Spiking Neural Networks by Temporal Mutual Information Mengting Xu, Shi Gu, Peng Lin, De Ma, Huajin Tang, Qian Zheng, Gang Pan The IEEE/CVF Conference on Computer Vision and Pattern Recognition* (CVPR), Jun 2026 [Project] Show that spike-based information transmission from SNNs inherently induce lower mutual information compared to spatial information transmission from ANNs, enabling a more compact upper bound on model robustness error and enhancing overall robustness
	S³: Spiking Neurons as an Isolating Segmenter for Brain Signal Decoding Qian Zheng^#, Ming Chen^#, Sha Zhao, Shi Gu, Peng Lin, De Ma, Huajin Tang, Gang Pan Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Feb 2026 [paper][code] Show the necessarity of reset mechanism from SNs for EEG signal segmentation Consistent performance improvement of two EEG foundation models by SN-based segmenter Interpretable EEG segmentation results
	Training High Performance Spiking Neural Network by Temporal Model Calibration Jiaqi Yan, Changping Wang, De Ma, Huajin Tang, Qian Zheng, Gang Pan International Conference on Machine Learning (ICML), Jul 2025 [paper][code] Show why TET and SDT struggle in SNN training based on gradient analysis Highest reported SNN accuracy (up to Jun 2025): 85.83% (ImageNet-1K) and 87.63±0.15% (CIFAR10-DVS)
	Spiking GS: Towards High-Accuracy and Low-Cost Surface Reconstruction via Spiking Neuron-based Gaussian Splatting Weixing Zhang^#, Zongrui Li^#, De Ma, Huajin Tang, Xudong Jiang, Qian Zheng, Gang Pan arXiv preprint arXiv:2410.07266* (Arxiv), Oct 2024 [paper][code] SNs to reduce excessive Gaussians Faster, lower storage, and higher accuracy 3DGS-based surface reconstruction
	Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation Zhanfeng Liao, Yan Liu, Qian Zheng, Gang Pan Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Feb 2024 (Oral) [paper][code][VALSE 论文速览] SNs to align the real-world observation of density discontinuity An adaptive thresholding method for NeRF density pruning
	Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN Yangfan Hu^#, Qian Zheng^#, Xudong Jiang, Gang Pan* IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Dec 2023 [paper][code] Highest reported SNN accuracy (up to Jun 2025): object detection (mAP: 73.43%, time steps: 7, PASCAL VOC 2007), and semantic segmentation (mIoU: 69.7%, time steps: 15, PASCAL VOC 2012)

Event Camera based Computer Vision

	eRetinexGS: Retinex Modeling for Low-Light Scene Enhancement via Event Streams and 3D Gaussian Splatting Haojie Yan, Zehao Chen, Yan Liu, Shi Gu, Peng Lin, De Ma, Huajin Tang, Qian Zheng, Gang Pan The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2026 [Project] Twe cues of event guided low-light enhancement A low-light enhancement framework combining Retinex decomposition with 3DGS
	E-NeMF: Event-based Neural Motion Field for Novel Space-time View Synthesis of Dynamic Scenes Yan Liu, Zehao Chen, Haojie Yan, De Ma, Huajin Tang, Qian Zheng, Gang Pan International Conference on Computer Vision (ICCV), Oct 2025 [paper][code] First work of event guided dynamic scenes reconstruction from a monocular event-frame video Use event streams to reconstruct accurate complex motion while free from the impact of event noise and sparsity
	EvHDR-NeRF: Building High Dynamic Range Radiance Fields with Single Exposure Images and Events Zehao Chen, Zhanfeng Liao, De Ma, Huajin Tang, Qian Zheng, Gang Pan Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Feb 2025 [paper][code] First work of event guided HDR radiance field reconstruction from a monocular and single-exposured event-frame video Faithfully reconstruct Camera Response Function (CRF)
	EvSTVSR: Event Guided Space-Time Video Super-Resolution Haojie Yan, Zhan Lu, Zehao Chen, De Ma, Huajin Tang, Qian Zheng*, Gang Pan Proceedings of the AAAI Conference on Artificial Intelligence* (AAAI), Feb 2025 [paper][code] Fewer is Better: fewer adjacent frames (with event streams) produce better results of space-time video super-resolution
	Event-ID: Intrinsic Decomposition Using an Event Camera Zehao Chen^#, Zhan Lu^#, De Ma, Huajin Tang, Qian Zheng, Gang Pan ACM International Conference on Multimedia (MM), Oct 2024 [paper][code] First work of event guided intrinsic decomposition from a event-frame video A framework enables geometry, materials, lighting recovery, and image relighting

🌏 Activities

Associate Editor: Pattern Recognition (2026.2 - present); IEEE Transactions on Cognitive and Developmental Systems (2024.12 - present); Neurocomputing (2023.10 - present)
Area Chair: BMVC 2026; ICME 2026; MIND 2025; PRCV 2023, 2025, 2026
Reviewer: TPAMI, IJCV, TIP, TMM, TNNLS, TCSVT; CVPR, ICCV, ECCV, ICLR, ICML, NeurIPS, AAAI, ACM MM, SIGGRAPH, IJCAI, ICME, BMVC, WACV
Committee Member: Executive Area Chair Committee of the Vision And Learning Seminar (2024/2025 副主席委员, 2026 主席委员); The Branch of Consciousness Science of the Chinese Cognitive Science Society (中国认知科学学会意识科学分会委员); Younth Working Committee of Chinese Association for Artificial Intelligence (中国人工智能协会青年工作委员会委员)
Conference Organizer: Publicity Chair: BMVC 2026, VALSE 2026; Tutorial Chair: ChinaBMI 2025, VALSE 2023 (5000+ attendees); Poster Chair: VALSE 2025 (5900+ attendees); Registration Chair: ChinaBMI 2024 (1000+ attendees); Finance Chair: IEEE CIS-RAM 2024; APR Chair: VALSE 2024 (5000+ attendees)
Workshop Organizer: The Second Young Scholars Workshop on Neuromorphic Computing, MIND 2025; Brain-inspired Intelligence and Technology , Academic Conference of China Instrument and Control Society 2025; The First Young Scholars Workshop on Neuromorphic Computing, IEEE CIS-RAM 2024; Brain-Inspired Vision and Learning, VALSE 2024
Others: CVPR 2025 Outstanding Reviewer (711/12593); CVPR 2024 Outstanding Reviewer; ACM Rising Star, Hangzhou Chapter, 2024; Excellent Research Fellow 2021, Nanyang Technological University (top 10%); BMVC 2020 Outstanding Reviewer; Outstanding Doctoral Dissertation Fellowship, Zhejiang University, 2017

📆 Teaching

Undergraduate: CS3140M: Theory of Computation, Zhejiang University, 2025; 21120520: Theory of Computation, Zhejiang University, 2023-2024
Graduate: 2122021002: Computer Vision, Zhejiang University, 2025; 22124095002: Machine Learning, Zhejiang University, 2023-2025

	eRetinexGS: Retinex Modeling for Low-Light Scene Enhancement via Event Streams and 3D Gaussian Splatting Haojie Yan, Zehao Chen, Yan Liu, Shi Gu, Peng Lin, De Ma, Huajin Tang, Qian Zheng, Gang Pan The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2026 [Project] Twe cues of event guided low-light enhancement A low-light enhancement framework combining Retinex decomposition with 3DGS
	E-NeMF: Event-based Neural Motion Field for Novel Space-time View Synthesis of Dynamic Scenes Yan Liu, Zehao Chen, Haojie Yan, De Ma, Huajin Tang, Qian Zheng, Gang Pan International Conference on Computer Vision (ICCV), Oct 2025 [paper][code] First work of event guided dynamic scenes reconstruction from a monocular event-frame video Use event streams to reconstruct accurate complex motion while free from the impact of event noise and sparsity
	EvHDR-NeRF: Building High Dynamic Range Radiance Fields with Single Exposure Images and Events Zehao Chen, Zhanfeng Liao, De Ma, Huajin Tang, Qian Zheng, Gang Pan Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Feb 2025 [paper][code] First work of event guided HDR radiance field reconstruction from a monocular and single-exposured event-frame video Faithfully reconstruct Camera Response Function (CRF)
	EvSTVSR: Event Guided Space-Time Video Super-Resolution Haojie Yan, Zhan Lu, Zehao Chen, De Ma, Huajin Tang, Qian Zheng*, Gang Pan Proceedings of the AAAI Conference on Artificial Intelligence* (AAAI), Feb 2025 [paper][code] Fewer is Better: fewer adjacent frames (with event streams) produce better results of space-time video super-resolution
	Event-ID: Intrinsic Decomposition Using an Event Camera Zehao Chen^#, Zhan Lu^#, De Ma, Huajin Tang, Qian Zheng, Gang Pan ACM International Conference on Multimedia (MM), Oct 2024 [paper][code] First work of event guided intrinsic decomposition from a event-frame video A framework enables geometry, materials, lighting recovery, and image relighting

Qian Zheng 郑 乾