Yi Zhan

Yi Zhan

Auto-generated profile, based on publicly available information

Yi Zhan

Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 June 2025 in IEEE Access
Verified
Journal Article
Open access
XZXiaohui Zhang
Xiaohui Zhang
ZYZenghui Yu
Zenghui Yu
SQShushan Qiao
Shushan Qiao
YZYi Zhan
Yi Zhan
This paper proposes a novel Fast Fourier Transform hardware architecture for natural-order multi-input multi-output processing, which is based on approximate computing and the block floating-point data format. The architecture innovatively combines the low-power characteristics of approximate multipliers with the high-precision advantages of block floating-point data formats, enabling efficient processing of 2048-point and 4096-point Fast Fourier Transform data. By employing conflict-free memory access techniques, the design optimizes data scheduling, reduces idle cycles during processing, and significantly enhances energy efficiency while maintaining computational accuracy. Experimental validation demonstrates that the processor, fabricated using a 40nm process, achieves a compact chip area of 0.42 mm². Operating at a frequency of 671.14 MHz, it delivers a throughput of 1073.82 MS/s for 4096-point FFT computations, with a power consumption of only 110.85 mW and a signal-quantization-to-noise ratio of 58.51 dB. Compared to state-of-the-art designs, this architecture achieves breakthrough improvements in throughput performance while maintaining competitive energy efficiency.

26 May 2026 in Neurocomputing
Verified
Journal Article
Closed access
JLJun Li
Jun Li
QLQiang Li
Qiang Li
YJYiying Jiang
Yiying Jiang
JZJionghao Zhang
Jionghao Zhang
HZHailong Zou
Hailong Zou
SQShushan Qiao
Shushan Qiao

8 May 2026 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
JZJionghao Zhang
Jionghao Zhang
YJYiying Jiang
Yiying Jiang
QLQiang Li
Qiang Li
GLGang Li
Gang Li
HRHang Ran
Hang Ran
SQShushan Qiao
Shushan Qiao
The energy efficiency of object detection processors based on traditional artificial neural networks (ANNs) is constrained by intensive multiply-accumulate operations and frequent memory accesses. Spiking neural networks (SNNs), characterized by biological plausibility, multiplier-free computation, and inherent sparsity, offer a promising alternative for energy-efficient inference. However, deploying SNNs for high-resolution object detection faces three key challenges: 1) long time-steps to maintain accuracy; 2) redundant weight access across time-steps; and 3) substantial external memory access (EMA) incurred by intermediate feature maps (FM). To address the above challenges, a dedicated SNN processor is presented with three contributions: 1) a customized short time-step quantized spiking YOLO (QS-YOLO) model, achieving 65.80-72.90% mAP on VOC2007 within only 1–4 time-steps through a progressive temporal compression (PTC) and quantization framework; 2) a novel weight-locally-distributed stationary spatio-temporal sequential interleaving (WLS-STS) dataflow, enabling single weight access across all time-steps while supporting flexible time-step configuration without loss of processing element (PE) utilization; and 3) a workload-aware dynamic global buffer allocation strategy to eliminate FM-EMA. The proposed processor incorporates a heterogeneous dual-core architecture, comprising a spike-driven accumulate unit (SAU) and a multiply–accumulate unit (MAU), to efficiently accelerate both spiking and non-spiking operators in QS-YOLO. Implemented on XCVU13P FPGA, the processor achieves a peak energy efficiency of 146.48 GOPS/W at 100MHz. Compared with existing object detection FPGA processors, the proposed processor achieves state-of-the-art energy efficiency.

12 January 2026 in IEEE Solid-State Circuits Letters
Verified
Journal Article
Closed access
XLXiaofeng Li
Xiaofeng Li
YZYi Zhan
Yi Zhan
PZPurui Zhu
Purui Zhu
RZRui Zhou
Rui Zhou
JSJiayin Song
Jiayin Song
SQShushan Qiao
Shushan Qiao
This paper presents an approximate digital compute-in-memory (CIM) macro for low-power edge AI inference. It introduces three hierarchical innovations: 1) novel fused approximate multiply-add units (FAMUs) that reduces power and area consumption; 2) a bit-critical weight allocation architecture that optimally balances accuracy and hardware cost; and 3) a dynamic sparsity-adaptive configuration method to minimize accuracy loss in real-time. The macro achieves an energy efficiency of 60.35 TOPS/W and an area efficiency of 1105 GOPS/mm for INT8 MACs, outperforming prior works. It attains negligible accuracy degradation on multiple mainstream datasets and suits well for edge AI inference.

18 February 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HZHailong Zou
Hailong Zou
JZJionghao Zhang
Jionghao Zhang
JLJun Li
Jun Li
HRHang Ran
Hang Ran
WYWulve Yang
Wulve Yang
SQShushan Qiao
Shushan Qiao
The hardware power-aware keyword spotting (KWS) implementation requires small memory footprint, low-complex computation, and high accuracy performances. Binary neural networks (BNNs) naturally satisfy these constraints. They quantize both weights and activations to 1-bit. This reduces storage and replaces most multiply–accumulate operations with bitwise operations. However, such extreme quantization incurs substantial information loss and leaves a noticeable accuracy gap relative to full-precision models. Optimization is also more difficult because the sign function is non-differentiable, and surrogate-gradient updates introduce gradient mismatch. To preserve the hardware benefits of BNNs while alleviating the accuracy degeneration induced by 1-bit quantization, this article addresses the problem from two complementary aspects: Firstly, a Stepwise Self-Knowledge Distillation (SSKD) training approach is proposed to effectively improve the student BNN’s accuracy performance. The SSKD training framework achieves effective supervision for student BNNs. A Stepwise Training Strategy is proposed to optimize the training stability and accuracy. Weight Scaling Factor improves the student’s representational capability. Secondly, an extremely lightweight Binary Temporal Convolutional ResNet (BTC-ResNet) is also proposed. The parameters and calculations inside the network are greatly reduced for the inference. Experiments on the GSCD v1 and GSCD v2 benchmarks demonstrate the effectiveness of our methods for low-power keyword spotting. For the 12-class task, BTC-ResNet14 achieves 97.23% accuracy on GSCD v1 and 97.31% on GSCD v2 with 0.75 Mb parameters and 1.35 M FLOPs. For the 35-class task on GSCD v2, it reaches 95.56% accuracy with 0.76 Mb parameters and 1.35 M FLOPs. These results indicate that our method achieves a competitive accuracy–efficiency balance relative to recent distillation-based BNN KWS baselines reported in the comparative experiments. All these studies are helpful and promising for future KWS deployment on low-power hardware devices.

1 January 2026 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
WYWulue Yang
Wulue Yang
HZHailong Zou
Hailong Zou
RZRui Zhou
Rui Zhou
JZJionghao Zhang
Jionghao Zhang
QLQiang Li
Qiang Li
SQShushan Qiao
Shushan Qiao