Cen Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Cen Chen has a total of 212 co-authors. Here are the top co-authors by number of shared publications:
- Kenli Li
Hunan University
18 shared publications - Xiaofeng Zou
South China University of Technology
18 shared publications - Yangfan Li
Central South University
13 shared publications - Huiping Zhuang
South China University of Technology
12 shared publications - Zeng Zeng
School of microelectronics, Shanghai University, Shanghai, China
11 shared publications - Keqin Li
Hunan University
10 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (12) , 4135-4149
Full-Chip Thermal Monitoring in Silicon-Photonic Chiplet Systems: Repurposing the Photonic Interposer Network
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (12) , 4135-4149
Full-Chip Thermal Monitoring in Silicon-Photonic Chiplet Systems: Repurposing the Photonic Interposer Network
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16307-16315
Clarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16307-16315
Open AccessClarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 45 (11) , 5960-5973
SimVidT: Video Transformer Acceleration via Exploiting Spatio-Temporal Similarity
Video transformers (VidTs) have demonstrated powerful spatio-temporal modelling capabilities in various video understanding tasks. However, their practical deployment remains constrained by high computational and memory overheads, primarily caused by the quadratic complexity of spatio-temporal self-attention and the intensive demands of processing high-frame-rate video streams. While recent efforts have attempted to leverage spatio-temporal similarity to eliminate redundant computation, they either rely on expensive similarity recognition or support only limited reuse, resulting in limited performance gains. In this work, we present a comprehensive analysis of the potential opportunities and challenges in exploiting spatiotemporal similarity within VidTs. Building upon these insights, we propose SimVidT, a novel VidT accelerator that leverages spatio-temporal similarity to reduce computational redundancy. SimVidT is supported by an algorithm and architecture codesign. At the algorithm level, we introduce a locality-aware similarity identification method and a redundancy-eliminated attention mechanism to efficiently identify and eliminate redundant computations at multiple granularities. At the architecture level, we develop a dedicated accelerator featuring a customized hierarchical memory management unit and specialized compute units, which adapts to the complex execution flow of VidTs and translates redundancy reduction into performance gains. We implement a cycle-accurate simulator for performance evaluation. Experimental results demonstrate that SimVidT achieves 1.7×speedup and 2.5× better energy efficiency on average compared to the state-of-the-art VidT accelerator CMC.
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 45 (11) , 5960-5973
SimVidT: Video Transformer Acceleration via Exploiting Spatio-Temporal Similarity
Video transformers (VidTs) have demonstrated powerful spatio-temporal modelling capabilities in various video understanding tasks. However, their practical deployment remains constrained by high computational and memory overheads, primarily caused by the quadratic complexity of spatio-temporal self-attention and the intensive demands of processing high-frame-rate video streams. While recent efforts have attempted to leverage spatio-temporal similarity to eliminate redundant computation, they either rely on expensive similarity recognition or support only limited reuse, resulting in limited performance gains. In this work, we present a comprehensive analysis of the potential opportunities and challenges in exploiting spatiotemporal similarity within VidTs. Building upon these insights, we propose SimVidT, a novel VidT accelerator that leverages spatio-temporal similarity to reduce computational redundancy. SimVidT is supported by an algorithm and architecture codesign. At the algorithm level, we introduce a locality-aware similarity identification method and a redundancy-eliminated attention mechanism to efficiently identify and eliminate redundant computations at multiple granularities. At the architecture level, we develop a dedicated accelerator featuring a customized hierarchical memory management unit and specialized compute units, which adapts to the complex execution flow of VidTs and translates redundancy reduction into performance gains. We implement a cycle-accurate simulator for performance evaluation. Experimental results demonstrate that SimVidT achieves 1.7×speedup and 2.5× better energy efficiency on average compared to the state-of-the-art VidT accelerator CMC.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (10) , 3599-3613
HDQAtt: A Photonic Transformer Accelerator via Hierarchical Dynamic Precision Quantification
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (10) , 3599-3613
HDQAtt: A Photonic Transformer Accelerator via Hierarchical Dynamic Precision Quantification
- 10 September 2026
- Published by Elsevier in Journal of Systems Architecture
- Vol. 181
S-GPT: Shape-aware graph partitioning and tuning for sustainable inference of large-scale deep neural networks
- 10 September 2026
- Published by Elsevier in Journal of Systems Architecture
- Vol. 181
S-GPT: Shape-aware graph partitioning and tuning for sustainable inference of large-scale deep neural networks
- 9 September 2026
- Published by Springer Nature
- p. 678-695
X-SG$^2$S: Safe and Generalizable Gaussian Splatting with X-Dimensional Watermarks- 9 September 2026
- Published by Springer Nature
- p. 678-695
X-SG$^2$S: Safe and Generalizable Gaussian Splatting with X-Dimensional Watermarks- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
UNICON: A Unified Reconfigurable Nonlinear Architecture for Efficient Neural Network Inference
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessUNICON: A Unified Reconfigurable Nonlinear Architecture for Efficient Neural Network Inference
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
DeltaSight: Architecting Efficient Video AIoT Systems via Cross-Stage Consistent Redundancy Elimination
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessDeltaSight: Architecting Efficient Video AIoT Systems via Cross-Stage Consistent Redundancy Elimination
- 8 July 2026
- Published by Elsevier in Journal of Systems Architecture
- Vol. 179
OMEC: Optimization of memory-efficient convolutions for multi-core edge devices
- 8 July 2026
- Published by Elsevier in Journal of Systems Architecture
- Vol. 179
OMEC: Optimization of memory-efficient convolutions for multi-core edge devices
- 9 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Cross-Modality Anatomy Knowledge Distillation for Retinal OCT Layer Segmentation with Limited Labels
Automatic segmentation of retinal Optical Coher ence Tomography (OCT) images plays a vital role in the early diagnosis and treatment of ocular diseases. However, the scarcity of labeled OCT data poses a significant challenge for existing supervised learning methods. In contrast, Color Fundus Photography (CFP) provides clearer visualization of key anatomical regions, such as the optic disc and cup, making it easier to acquire high-quality annotations. To address the issue of insufficient OCT annotations, we propose a Cross-Modality Anatomy Knowledge Distillation (CMAKD) framework. This method leverages a large amount of annotated CFP data to learn cross-modality structural priors related to retinal layer organization and vessel-associated landmarks, which are then used to regularize the OCT model for retinal layer segmentation. In other words, CFP serves as a source of weak structural priors, providing spatial and contextual guidance for OCT feature learning rather than depth-resolved layer supervision or a direct supervisory signal. To achieve this goal, we design a Domain-invariant Contrastive Learning (DoCL) module to reduce the modality gap between CFP and OCT by aligning their feature distributions. Furthermore, we introduce a Layer-aware Self-ensembling Mean-Teacher (LA-MT) framework to fully exploit unlabeled OCT data and enhance the model’s ability to recognize layered boundary structures. Experimental results on three public datasets — Duke DME, MS, and GOALS — demonstrate that CMAKD significantly improves segmentation performance while reducing the reliance on OCT annotations. Under semi-supervised domain adaptation settings, CMAKD achieves relative performance gains of 17.8% and 8.2% on the Duke DME and MS datasets, respectively, and approaches the performance of fully supervised models on the GOALS dataset. Our code is available at: https://github.com/lixiangcog/CMAKD.
- 9 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Cross-Modality Anatomy Knowledge Distillation for Retinal OCT Layer Segmentation with Limited Labels
Automatic segmentation of retinal Optical Coher ence Tomography (OCT) images plays a vital role in the early diagnosis and treatment of ocular diseases. However, the scarcity of labeled OCT data poses a significant challenge for existing supervised learning methods. In contrast, Color Fundus Photography (CFP) provides clearer visualization of key anatomical regions, such as the optic disc and cup, making it easier to acquire high-quality annotations. To address the issue of insufficient OCT annotations, we propose a Cross-Modality Anatomy Knowledge Distillation (CMAKD) framework. This method leverages a large amount of annotated CFP data to learn cross-modality structural priors related to retinal layer organization and vessel-associated landmarks, which are then used to regularize the OCT model for retinal layer segmentation. In other words, CFP serves as a source of weak structural priors, providing spatial and contextual guidance for OCT feature learning rather than depth-resolved layer supervision or a direct supervisory signal. To achieve this goal, we design a Domain-invariant Contrastive Learning (DoCL) module to reduce the modality gap between CFP and OCT by aligning their feature distributions. Furthermore, we introduce a Layer-aware Self-ensembling Mean-Teacher (LA-MT) framework to fully exploit unlabeled OCT data and enhance the model’s ability to recognize layered boundary structures. Experimental results on three public datasets — Duke DME, MS, and GOALS — demonstrate that CMAKD significantly improves segmentation performance while reducing the reliance on OCT annotations. Under semi-supervised domain adaptation settings, CMAKD achieves relative performance gains of 17.8% and 8.2% on the Duke DME and MS datasets, respectively, and approaches the performance of fully supervised models on the GOALS dataset. Our code is available at: https://github.com/lixiangcog/CMAKD.