Xunzhao Yin

Yu Fu, Yanyan Huang, Yalin Wang et al.

Chronological age of healthy brain is able to be predicted using deep neural networks from T1-weighted magnetic resonance images (T1 MRIs), and the predicted brain age could serve as an effective biomarker for detecting aging-related diseases or disorders. In this paper, we propose an end-to-end neural network architecture, referred to as optimal transport based feature pyramid fusion (OTFPF) network, for the brain age estimation with T1 MRIs. The OTFPF consists of three types of modules: Optimal Transport based Feature Pyramid Fusion (OTFPF) module, 3D overlapped ConvNeXt (3D OL-ConvNeXt) module and fusion module. These modules strengthen the OTFPF network's understanding of each brain's semi-multimodal and multi-level feature pyramid information, and significantly improve its estimation performances. Comparing with recent state-of-the-art models, the proposed OTFPF converges faster and performs better. The experiments with 11,728 MRIs aged 3-97 years show that OTFPF network could provide accurate brain age estimation, yielding mean absolute error (MAE) of 2.097, Pearson's correlation coefficient (PCC) of 0.993 and Spearman's rank correlation coefficient (SRCC) of 0.989, between the estimated and chronological ages. Widespread quantitative experiments and ablation experiments demonstrate the superiority and rationality of OTFPF network. The codes and implement details will be released on GitHub: https://github.com/ZJU-Brain/OTFPF after final decision.

Wenhao Sun, Bing Li, Grace Li Zhang et al.

While large language models (LLMs) have demonstrated the ability to generate hardware description language (HDL) code for digital circuits, they still suffer from the hallucination problem, which leads to the generation of incorrect HDL code or misunderstanding of specifications. In this work, we introduce a human-expert-inspired method to mitigate the hallucination of LLMs and improve the performance in HDL code generation. We first let LLMs classify the type of the circuit based on the specifications. Then, according to the type of the circuit, we split the tasks into several sub-procedures, including information extraction and human-like design flow using Electronic Design Automation (EDA) tools. Besides, we also use a search method to mitigate the variation in code generation. Experimental results show that our method can significantly improve the functional correctness of the generated Verilog and reduce the hallucination of LLMs.

Xiao Dong, Yufei Chen, Xunzhao Yin et al.

Worst-case dynamic PDN noise analysis is an essential step in PDN sign-off to ensure the performance and reliability of chips. However, with the growing PDN size and increasing scenarios to be validated, it becomes very time- and resource-consuming to conduct full-stack PDN simulation to check the worst-case noise for different test vectors. Recently, various works have proposed machine learning based methods for supply noise prediction, many of which still suffer from large training overhead, inefficiency, or non-scalability. Thus, this paper proposed an efficient and scalable framework for the worst-case dynamic PDN noise prediction. The framework first reduces the spatial and temporal redundancy in the PDN and input current vector, and then employs efficient feature extraction as well as a novel convolutional neural network architecture to predict the worst-case dynamic PDN noise. Experimental results show that the proposed framework consistently outperforms the commercial tool and the state-of-the-art machine learning method with only 0.63-1.02% mean relative error and 25-69$\times$ speedup.

Wenhao Sun, Grace Li Zhang, Xunzhao Yin et al.

Deep neural networks (DNNs) have successfully been applied in many fields in the past decades. However, the increasing number of multiply-and-accumulate (MAC) operations in DNNs prevents their application in resource-constrained and resource-varying platforms, e.g., mobile phones and autonomous vehicles. In such platforms, neural networks need to provide acceptable results quickly and the accuracy of the results should be able to be enhanced dynamically according to the computational resources available in the computing system. To address these challenges, we propose a design framework called SteppingNet. SteppingNet constructs a series of subnets whose accuracy is incrementally enhanced as more MAC operations become available. Therefore, this design allows a trade-off between accuracy and latency. In addition, the larger subnets in SteppingNet are built upon smaller subnets, so that the results of the latter can directly be reused in the former without recomputation. This property allows SteppingNet to decide on-the-fly whether to enhance the inference accuracy by executing further MAC operations. Experimental results demonstrate that SteppingNet provides an effective incremental accuracy improvement and its inference accuracy consistently outperforms the state-of-the-art work under the same limit of computational resources.

Chuangtao Chen, Grace Li Zhang, Xunzhao Yin et al.

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for shifts in attention distribution. Existing solutions such as CacheBlend, EPIC, and SAM-KV mitigate this issue by selectively recomputing a subset of tokens; however, they still incur non-negligible computational overhead (FLOPs) and increased Time-to-First-Token (TTFT) latency. In this paper, we propose KV Packet, a recomputation-free cache reuse framework that treats cached documents as immutable ``packets'' wrapped in light-weight trainable soft-token adapters, which are trained via self-supervised distillation to bridge context discontinuities. Experiments on Llama-3.1 and Qwen2.5 demonstrate that the proposed KV Packet method achieves near-zero FLOPs and lower TTFT than recomputation-based baselines, while retaining F1 scores comparable to those of the full recomputation baseline.

Amro Eldebiky, Grace Li Zhang, Xunzhao Yin et al.

Deep neural networks (DNNs) have made breakthroughs in various fields including image recognition and language processing. DNNs execute hundreds of millions of multiply-and-accumulate (MAC) operations. To efficiently accelerate such computations, analog in-memory-computing platforms have emerged leveraging emerging devices such as resistive RAM (RRAM). However, such accelerators face the hurdle of being required to have sufficient on-chip crossbars to hold all the weights of a DNN. Otherwise, RRAM cells in the crossbars need to be reprogramed to process further layers, which causes huge time/energy overhead due to the extremely slow writing and verification of the RRAM cells. As a result, it is still not possible to deploy such accelerators to process large-scale DNNs in industry. To address this problem, we propose the BasisN framework to accelerate DNNs on any number of available crossbars without reprogramming. BasisN introduces a novel representation of the kernels in DNN layers as combinations of global basis vectors shared between all layers with quantized coefficients. These basis vectors are written to crossbars only once and used for the computations of all layers with marginal hardware modification. BasisN also provides a novel training approach to enhance computation parallelization with the global basis vectors and optimize the coefficients to construct the kernels. Experimental results demonstrate that cycles per inference and energy-delay product were reduced to below 1% compared with applying reprogramming on crossbars in processing large-scale DNNs such as DenseNet and ResNet on ImageNet and CIFAR100 datasets, while the training and hardware costs are negligible.

Chuangtao Chen, Grace Li Zhang, Xunzhao Yin et al.

Deep neural networks (DNNs) have been widely deployed across diverse domains such as computer vision and natural language processing. However, the impressive accomplishments of DNNs have been realized alongside extensive computational demands, thereby impeding their applicability on resource-constrained devices. To address this challenge, many researchers have been focusing on basic neuron structures, the fundamental building blocks of neural networks, to alleviate the computational and storage cost. In this work, an efficient quadratic neuron architecture distinguished by its enhanced utilization of second-order computational information is introduced. By virtue of their better expressivity, DNNs employing the proposed quadratic neurons can attain similar accuracy with fewer neurons and computational cost. Experimental results have demonstrated that the proposed quadratic neuron structure exhibits superior computational and storage efficiency across various tasks when compared with both linear and non-linear neurons in prior work.

Bo Liu, Grace Li Zhang, Xunzhao Yin et al.

Deep neural networks (DNNs) have achieved great breakthroughs in many fields such as image classification and natural language processing. However, the execution of DNNs needs to conduct massive numbers of multiply-accumulate (MAC) operations on hardware and thus incurs a large power consumption. To address this challenge, we propose a novel digital MAC design based on encoding. In this new design, the multipliers are replaced by simple logic gates to represent the results with a wide bit representation. The outputs of the new multipliers are added by bit-wise weighted accumulation and the accumulation results are compatible with existing computing platforms accelerating neural networks. Since the multiplication function is replaced by a simple logic representation, the critical paths in the resulting circuits become much shorter. Correspondingly, pipelining stages and intermediate registers used to store partial sums in the MAC array can be reduced, leading to a significantly smaller area as well as better power efficiency. The proposed design has been synthesized and verified by ResNet18- Cifar10, ResNet20-Cifar100, ResNet50-ImageNet, MobileNetV2-Cifar10, MobileNetV2-Cifar100, and EfficientNetB0-ImageNet. The experimental results confirmed the reduction of circuit area by up to 48.79% and the reduction of power consumption of executing DNNs by up to 64.41%, while the accuracy of the neural networks can still be well maintained. The open source code of this work can be found on GitHub with link https://github.com/Bo-Liu-TUM/EncodingNet/.

Chao Li, Zhicheng Xu, Bo Wen et al.

In scenarios with limited training data or where explainability is crucial, conventional neural network-based machine learning models often face challenges. In contrast, Bayesian inference-based algorithms excel in providing interpretable predictions and reliable uncertainty estimation in these scenarios. While many state-of-the-art in-memory computing (IMC) architectures leverage emerging non-volatile memory (NVM) technologies to offer unparalleled computing capacity and energy efficiency for neural network workloads, their application in Bayesian inference is limited. This is because the core operations in Bayesian inference differ significantly from the multiplication-accumulation (MAC) operations common in neural networks, rendering them generally unsuitable for direct implementation in most existing IMC designs. In this paper, we propose FeBiM, an efficient and compact Bayesian inference engine powered by multi-bit ferroelectric field-effect transistor (FeFET)-based IMC. FeBiM effectively encodes the trained probabilities of a Bayesian inference model within a compact FeFET-based crossbar. It maps quantized logarithmic probabilities to discrete FeFET states. As a result, the accumulated outputs of the crossbar naturally represent the posterior probabilities, i.e., the Bayesian inference model's output given a set of observations. This approach enables efficient in-memory Bayesian inference without the need for additional calculation circuitry. As the first FeFET-based in-memory Bayesian inference engine, FeBiM achieves an impressive storage density of 26.32 Mb/mm$^{2}$ and a computing efficiency of 581.40 TOPS/W in a representative Bayesian classification task. These results demonstrate 10.7$\times$/43.4$\times$ improvement in compactness/efficiency compared to the state-of-the-art hardware implementation of Bayesian inference.

Bo Wen, Guoyun Gao, Zhicheng Xu et al.

The rapid advancement of artificial intelligence has raised concerns regarding its trustworthiness, especially in terms of interpretability and robustness. Tree-based models like Random Forest and XGBoost excel in interpretability and accuracy for tabular data, but scaling them remains computationally expensive due to poor data locality and high data dependence. Previous efforts to accelerate these models with analog content addressable memory (CAM) have struggled, due to the fact that the difficult-to-implement sharp decision boundaries are highly susceptible to device variations, which leads to poor hardware performance and vulnerability to adversarial attacks. This work presents a novel hardware-software co-design approach using $MoS_2$ Flash-based analog CAM with inherent soft boundaries, enabling efficient inference with soft tree-based models. Our soft tree model inference experiments on $MoS_2$ analog CAM arrays show this method achieves exceptional robustness against device variation and adversarial attacks while achieving state-of-the-art accuracy. Specifically, our fabricated analog CAM arrays achieve $96\%$ accuracy on Wisconsin Diagnostic Breast Cancer (WDBC) database, while maintaining decision explainability. Our experimentally calibrated model validated only a $0.6\%$ accuracy drop on the MNIST dataset under $10\%$ device threshold variation, compared to a $45.3\%$ drop for traditional decision trees. This work paves the way for specialized hardware that enhances AI's trustworthiness and efficiency.

Yifei Zhou, Xuchu Huang, Chenyu Ni et al.

Neuro-symbolic artificial intelligence (neuro-symbolic AI) excels in logical analysis and reasoning. Hyperdimensional Computing (HDC), a promising brain-inspired computational model, is integral to neuro-symbolic AI. Various HDC models have been proposed to represent class-instance and class-class relations, but when representing the more complex class-subclass relation, where multiple objects associate different levels of classes and subclasses, they face challenges for factorization, a crucial task for neuro-symbolic AI systems. In this article, we propose FactorHD, a novel HDC model capable of representing and factorizing the complex class-subclass relation efficiently. FactorHD features a symbolic encoding method that embeds an extra memorization clause, preserving more information for multiple objects. In addition, it employs an efficient factorization algorithm that selectively eliminates redundant classes by identifying the memorization clause of the target class. Such model significantly enhances computing efficiency and accuracy in representing and factorizing multiple objects with class-subclass relation, overcoming limitations of existing HDC models such as "superposition catastrophe" and "the problem of 2". Evaluations show that FactorHD achieves approximately 5667x speedup at a representation size of 10^9 compared to existing HDC models. When integrated with the ResNet-18 neural network, FactorHD achieves 92.48% factorization accuracy on the Cifar-10 dataset.

Chuangtao Chen, Grace Li Zhang, Xunzhao Yin et al.

In this paper, we introduce LiveMind, a novel low-latency inference framework for large language model (LLM) inference which enables LLMs to perform inferences with incomplete user input. By reallocating computational processes to the input phase, a substantial reduction in latency is achieved, thereby significantly enhancing the interactive experience for users of LLMs. The framework adeptly manages the visibility of the streaming input to the model, allowing it to infer from incomplete user input or await additional content. Compared with traditional inference methods on complete user input, our approach demonstrates an average reduction in response latency of 84.0% on the MMLU dataset and 71.6% on the MMLU-Pro dataset, while maintaining comparable accuracy. Additionally, our framework facilitates collaborative inference and output across different models. By employing an large LLM for inference and a small LLM for output, we achieve an average 37% reduction in response latency, alongside a 4.30% improvement in accuracy on the MMLU-Pro dataset compared with the baseline. The proposed LiveMind framework advances the field of human-AI interaction by enabling more responsive and efficient communication between users and AI systems.

Mengnan Jiang, Jingcun Wang, Amro Eldebiky et al.

Deep neural networks (DNNs) have demonstrated remarkable success in various fields. However, the large number of floating-point operations (FLOPs) in DNNs poses challenges for their deployment in resource-constrained applications, e.g., edge devices. To address the problem, pruning has been introduced to reduce the computational cost in executing DNNs. Previous pruning strategies are based on weight values, gradient values and activation outputs. Different from previous pruning solutions, in this paper, we propose a class-aware pruning technique to compress DNNs, which provides a novel perspective to reduce the computational cost of DNNs. In each iteration, the neural network training is modified to facilitate the class-aware pruning. Afterwards, the importance of filters with respect to the number of classes is evaluated. The filters that are only important for a few number of classes are removed. The neural network is then retrained to compensate for the incurred accuracy loss. The pruning iterations end until no filter can be removed anymore, indicating that the remaining filters are very important for many classes. This pruning technique outperforms previous pruning solutions in terms of accuracy, pruning ratio and the reduction of FLOPs. Experimental results confirm that this class-aware pruning technique can significantly reduce the number of weights and FLOPs, while maintaining a high inference accuracy.