Search Results - "Yue, Zhiheng"

Evaluation of astaxanthin stability under varying temperatures and ultraviolet irradiation durations based on Raman spectroscopy by Liu, Xiaodan, Li, Wenjing, Yue, Zhiheng, Qian, Jiangjin, Zhu, Wenjing, Dai, Huang, Wang, Jiahua, Pi, Fuwei

“…As a potent naturally carotenoid, Astaxanthin (AST) is commonly used as a natural coloring agent and antioxidant in food products, and it's stability is of…”
Get full text

Origin and significance of pre-mineralization pyrite in the Jinya gold deposit, northwestern Guangxi Province, China: in situ trace element and sulfur isotope constraints by Li, Xinhang, Bai, Lingan, Yu, Yong, Hu, Qiaofan, Pang, Baocheng, Wei, Dongtian, Xie, Lanfang, Yue, Zhiheng

“…The Jinya Au deposit is a typical Carlin-type deposit in the Golden Triangle of Yunnan, Guizhou, and Guangxi provinces, China. The ore bodies occur in the…”
Get full text

Reducing microplastics in tea infusions released from filter bags by pre-washing method: Quantitative evidences based on Raman imaging and Py-GC/MS by Yue, Zhiheng, Liu, Xiaodan, Mei, Tingna, Zhang, Yanpeng, Pi, Fuwei, Dai, Huang, Zhou, Yi, Wang, Jiahua

“…[Display omitted] •Estimation of micron-sized microplastics in tea infusion by Raman imaging.•Detection of submicron- and nano-sized microplastics in tea…”
Get full text

Adulteration detection of multi-species vegetable oils in camellia oil using Raman spectroscopy: Comparison of chemometrics and deep learning methods by Wang, Jiahua, Qian, Jiangjin, Xu, Mengting, Ding, Jianyu, Yue, Zhiheng, Zhang, Yanpeng, Dai, Huang, Liu, Xiaodan, Pi, Fuwei

“…Oil adulteration is a global challenge in the production of high value-added natural oils. Raman spectroscopy combined with mathematical modeling can be used…”
Get full text

BR-CIM: An Efficient Binary Representation Computation-In-Memory Design by Yue, Zhiheng, Wang, Yabing, Qin, Yubin, Liu, Leibo, Wei, Shaojun, Yin, Shouyi

“…Deep neural network (DNN) has recently attracted tremendous attention in various fields. But the computing operation requirement and the memory bottleneck…”
Get full text

CV-CIM: A Hybrid Domain Xor-Derived Similarity-Aware Computation-in-Memory Supporting Cost-Volume Construction by Yue, Zhiheng, Wang, Yang, Wang, Huizheng, Guo, Ruiqi, Tu, Fengbin, Yang, Jianxun, Wei, Shaojun, Hu, Yang, Yin, Shouyi

“…Cost-volume construction, a cornerstone of stereo vision processing, has been widely utilized across diverse domains such as robotics, autonomous vehicles, 3-D…”
Get full text

STAR: An STGCN ARchitecture for Skeleton-Based Human Action Recognition by Wu, Weiwei, Tu, Fengbin, Niu, Mengqi, Yue, Zhiheng, Liu, Leibo, Wei, Shaojun, Li, Xiangyu, Hu, Yang, Yin, Shouyi

“…Skeleton-based human action cognition (HAR) has drawn increasing attention recently. As an emerging approach for skeleton-based HAR tasks, Spatial-Temporal…”
Get full text

TT@CIM: A Tensor-Train In-Memory-Computing Processor Using Bit-Level-Sparsity Optimization and Variable Precision Quantization by Guo, Ruiqi, Yue, Zhiheng, Si, Xin, Li, Hao, Hu, Te, Tang, Limei, Wang, Yabing, Sun, Hao, Liu, Leibo, Chang, Meng-Fan, Li, Qiang, Wei, Shaojun, Yin, Shouyi

“…Computing-in-memory (CIM) is an attractive approach for energy-efficient deep neural network (DNN) processing, especially for low-power edge devices. However,…”
Get full text

A 28-nm 28.8-TOPS/W Attention-Based NN Processor With Correlative CIM Ring Architecture and Dataflow-Reshaped Digital-Assisted CIM Array by Guo, Ruiqi, Yue, Zhiheng, Wang, Yang, Li, Hao, Hu, Te, Wang, Yabing, Sun, Hao, Hsu, Jeng-Long, Zhang, Yaojun, Yan, Bonan, Liu, Leibo, Huang, Ru, Wei, Shaojun, Yin, Shouyi

“…Transformer models have achieved impressive performance in various applications by effectively capturing contextual knowledge from the entire sequence…”
Get full text

A 22nm 54.94TFLOPS/W Transformer Fine-Tuning Processor with Exponent-Stationary Re-Computing, Aggressive Linear Fitting, and Logarithmic Domain Multiplicating by Wang, Yang, Yang, Xiaolong, Qin, Yubin, Zhao, Zhiren, Guo, Ruiqi, Yue, Zhiheng, Han, Huiming, Wei, Shaojun, Hu, Yang, Yin, Shouyi

“…This paper proposes a Transformer-based processor supporting energy-efficient fine-tuning with batch-iteration-matrix multi-level optimizations. It has three…”
Get full text

34.1 A 28nm 83.23TFLOPS/W POSIT-Based Compute-in-Memory Macro for High-Accuracy AI Applications by Wang, Yang, Yang, Xiaolong, Qin, Yubin, Zhao, Zhiren, Guo, Ruiqi, Yue, Zhiheng, Han, Huiming, Wei, Shaojun, Hu, Yang, Yin, Shouyi

“…Rapidly expanding artificial intelligence (Al) models, for complex AI tasks, drive high-energy efficiency and high-precision requirements for Al processors…”
Get full text

15.1 A 0.795fJ/bit Physically-Unclonable Function-Protected TCAM for a Software-Defined Networking Switch by Yue, Zhiheng, Xiang, Xujiang, Tu, Fengbin, Wang, Yang, Wang, Yiming, Wei, Shaojun, Hu, Yang, Yin, Shouyi

“…As IoT devices proliferate, it is necessary to pay attention to how they interact within heterogeneous networks, where the packet type, protocol, and bandwidth…”
Get full text

20.2 A 28nm 74.34TFLOPS/W BF16 Heterogenous CIM-Based Accelerator Exploiting Denoising-Similarity for Diffusion Models by Guo, Ruiqi, Wang, Lei, Chen, Xiaofeng, Sun, Hao, Yue, Zhiheng, Qin, Yubin, Han, Huiming, Wang, Yang, Tu, Fengbin, Wei, Shaojun, Hu, Yang, Yin, Shouyi

“…Diffusion models (DMs) have emerged as a powerful category of generative models with record-breaking performance in image synthesis [1]. A noisy image created…”
Get full text

7.7 CV-CIM: A 28nm XOR-Derived Similarity-Aware Computation-in-Memory for Cost-Volume Construction by Yue, Zhiheng, Wang, Yang, Wang, Huizheng, Wang, Yabing, Guo, Ruiqi, Tang, Limei, Liu, Leibo, Wei, Shaojun, Hu, Yang, Yin, Shouyi

“…Cost-volume construction, which accurately computes the similarities between pixels in paired images, is a fundamental kernel of stereo vision processing and…”
Get full text

A 28nm 77.35TOPS/W Similar Vectors Traceable Transformer Processor with Principal-Component-Prior Speculating and Dynamic Bit-wise Stationary Computing by Wang, Yang, Qin, Yubin, Deng, Dazheng, Yang, Xiaolong, Zhao, Zhiren, Guo, Ruiqi, Yue, Zhiheng, Liu, Leibo, Wei, Shaojun, Hu, Yang, Yin, Shouyi

“…This paper proposes an energy-efficient Transformer processor exploiting dynamic similarity in global attention computing. It has three features: 1) A…”
Get full text

Exploiting Similarity Opportunities of Emerging Vision AI Models on Hybrid Bonding Architecture by Yue, Zhiheng, Wang, Huizheng, Fang, Jiahao, Deng, Jinyi, Lu, Guangyang, Tu, Fengbin, Guo, Ruiqi, Li, Yuxuan, Qin, Yubin, Wang, Yang, Li, Chao, Han, Huiming, Wei, Shaojun, Hu, Yang, Yin, Shouyi

“…While extensive research has focused on optimizing performance and efficiency in vision-based AI accelerators, an unexplored phenomenon, Clustering Similarity…”
Get full text

15.4 A 5.99-to-691.1TOPS/W Tensor-Train In-Memory-Computing Processor Using Bit-Level-Sparsity-Based Optimization and Variable-Precision Quantization by Guo, Ruiqi, Yue, Zhiheng, Si, Xin, Hu, Te, Li, Hao, Tang, Limei, Wang, Yabing, Liu, Leibo, Chang, Meng-Fan, Li, Qiang, Wei, Shaojun, Yin, Shouyi

“…Computing-in-memory (CIM) improves energy efficiency by enabling parallel multiply-and-accumulate (MAC) operations and reducing memory accesses [1 -4]…”
Get full text

A Systolic Computing-in-Memory Array based Accelerator with Predictive Early Activation for Spatiotemporal Convolutions by Chen, Xiaofeng, Guo, Ruiqi, Yue, Zhiheng, Hu, Yang, Liu, Leibo, Wei, Shaojun, Yin, Shouyi

“…Residual (2+1)-dimensional convolution neural network (R(2+1)D CNN) has achieved great success in video recognition due to the spatiotemporal convolution…”
Get full text

Efficient Orchestrated AI Workflows Execution on Scale-out Spatial Architecture by Deng, Jinyi, Tang, Xinru, Yue, Zhiheng, Lu, Guangyang, Yang, Qize, Zhang, Jiahao, Li, Jinxi, Li, Chao, Wei, Shaojun, Hu, Yang, Yin, Shouyi

“…Given the increasing complexity of AI applications, traditional spatial architectures frequently fall short. Our analysis identifies a pattern of…”
Get full text

SOFA: A Compute-Memory Optimized Sparsity Accelerator via Cross-Stage Coordinated Tiling by Wang, Huizheng, Fang, Jiahao, Tang, Xinru, Yue, Zhiheng, Li, Jinxi, Qin, Yubin, Guan, Sihan, Yang, Qize, Wang, Yang, Li, Chao, Hu, Yang, Yin, Shouyi

“…Benefiting from the self-attention mechanism, Transformer models have attained impressive contextual comprehension capabilities for lengthy texts. The…”
Get full text