Multiplication is a fundamental operation in many applications, and multipliers are widely adopted in various circuits. However, optimizing multipliers is challenging due to the extensive design space. In this article, we propose a multiplier design optimization framework based on reinforcement learning. We utilize matrix and tensor representations for the compressor tree of a multiplier, enabling seamless integration of convolutional neural networks as the agent network. The agent optimizes the multiplier structure using a Pareto-driven reward customized to balance area and delay. Furthermore, we enhance the original framework with parallel reinforcement learning and design space pruning techniques and extend its capability to optimize fused multiply-accumulate designs. Experiments conducted on different bit widths of multipliers demonstrate that multipliers produced by our approach outperform all baseline designs in terms of area, power, and delay. The performance gain is further validated by comparing the area, power, and delay of processing element arrays using multipliers from our approach and baseline approaches.

FPGAs have become a promising solution for accelerating deep learning (DL) workloads because of their inherent reconfigurability and heterogeneous architecture, which effectively handles specific computing tasks. Previous works have proposed various modifications to FPGA architectures for DL acceleration. However, they mainly focus on manual architecture designs, making it difficult to handle multiple scenarios and potentially limiting exploration of the search space. We propose a holistic automatic framework to explore FPGA architectures tailored for DL acceleration. By modifying and integrating CAD tools, we enable automated architecture generation and evaluation. This is combined with a multi-objective Tree-structured Parzen Estimator (TPE) algorithm to iterate the exploration process for finding optimal solutions. Experimental results show that the optimized architectures outperform all the baseline architectures in both delay and the area-delay product (ADP). Furthermore, our results achieve a 29.4% increase in hypervolume and an 89.5% reduction in average distance to reference set (ADRS).

The logic synthesis optimization flow is crucial to the quality of results (QoR), which applies a sequence of transformations to a design. Recently, there has been a growing focus on the automatic optimization of synthesis flows to improve QoR, utilizing techniques such as Bayesian optimization and reinforcement learning, which may fall short in efficiency due to the exponentially large search space. In contrast, continuous optimization offers notable efficiency advantages by leveraging the explicit gradient. However, despite its potential, several significant concerns remain to be addressed. On one hand, it is essential to obtain a reliable gradient. On the other hand, a major challenge arises from the fact that searching within a continuous space can yield solutions that deviate from feasible ones. In this paper, we propose an efficient approach to optimize synthesis sequences within a continuous latent space. Specifically, the gradient information is derived from a QoR surrogate model, while the discrepancies between solutions and feasible transformations are minimized by a diffusion model. Experimental results on extensive benchmarks demonstrate that the proposed method not only achieves lower area and delay but also improves efficiency by 5 X to 130 X, compared with previous methods.

ABSTRACT Forecasting the physical fitness of university students holds significant importance, as fitness is not only a key health indicator but also a critical factor influencing academic performance and overall well‐being. Accurate predictions of future fitness levels can inform targeted interventions, enabling institutions to enhance student health outcomes effectively. In this work, we propose a Bayesian neural network (BNN) approach for predicting student physical fitness. The proposed method offers two key advantages, one of which is that it provides confidence measures (e.g., prediction variance) alongside forecasts, and its inherent Bayesian framework helps mitigate overfitting, improving generalization. Our experimental results demonstrate that the proposed BNN model successfully predicts nine key physical fitness indicators while also identifying the most influential factors affecting prediction accuracy. Comparative evaluations show that our method outperforms baseline approaches, achieving a prediction accuracy of 93.7%. Notably, among the nine indicators, pull‐up and sit‐up performance exhibit a substantially stronger impact on overall fitness predictions compared to the other seven indicators. These findings underscore the efficacy of our Bayesian neural network in forecasting student physical fitness, offering a robust tool for educators and health professionals to support data‐driven fitness assessments and interventions.

Event cameras draw inspiration from biological systems, boasting low latency and high dynamic range while consuming minimal power. The most current approach to processing Event Cloud often involves converting it into frame-based representations, which neglects the sparsity of events, loses fine-grained temporal information, and increases the computational burden. In contrast, Point Cloud is a popular representation for processing 3-dimensional data and serves as an alternative method to exploit local and global spatial features. Nevertheless, previous point-based methods show an unsatisfactory performance compared to the frame-based method in dealing with spatio-temporal event streams. In order to bridge the gap, we propose EventMamba, an efficient and effective framework based on Point Cloud representation by rethinking the distinction between Event Cloud and Point Cloud, emphasizing vital temporal information. The Event Cloud is subsequently fed into a hierarchical structure with staged modules to process both implicit and explicit temporal features. Specifically, we redesign the global extractor to enhance explicit temporal extraction among a long sequence of events with temporal aggregation and State Space Model (SSM) based Mamba. Our model consumes minimal computational resources in the experiments and still exhibits SOTA point-based performance on six different scales of action recognition datasets. It even outperformed all frame-based methods on both Camera Pose Relocalization (CPR) and eye-tracking regression tasks.

Event cameras exhibit remarkable attributes such as high dynamic range, asynchronicity, and low latency, making them highly suitable for vision tasks that involve highspeed motion in challenging lighting conditions. These cameras implicitly capture movement and depth information in events, making them appealing sensors for Camera Pose Relocalization (CPR) tasks. Nevertheless, existing CPR networks based on events neglect the pivotal finegrained temporal information in events, resulting in unsatisfactory performance. Moreover, the energy-efficient features are further compromised by the use of excessively complex models, hindering efficient deployment on edge devices. In this paper, we introduce PEPNet, a simple and effective point-based network designed to regress six degrees of freedom (6-DOFs) event camera poses. We rethink the relationship between the event camera and CPR tasks, leveraging the raw Point Cloud directly as network input to harness the high-temporal resolution and inherent sparsity of events. PEPNet is adept at abstracting the spatial and implicit temporal features through hierarchical structure and explicit temporal features by Attentive Bidirectional Long Short-Term Memory (A-Bi-LSTM). Byemploying a carefully crafted lightweight design, PEPNet delivers state-of-the-art (SOTA) performance on both indoor and outdoor datasets with meager computational resources. Specifically, PEPNet attains a significant 38% and 33% performance improvement on the random split IJRR and M3ED datasets, respectively. Moreover, the lightweight design version PEPNettinyaccomplishes results comparable to the SOTA while employing a mere 0.5% of the parameters.

Multipliers and multiply-accumulators (MACs) are critical arithmetic circuit components in the modern era. As essential components of AI accelerators, they significantly influence the area and performance of compute-intensive circuits. This paper presents UFOMAC, a unified framework for the optimization of multipliers and MACs. Specifically, UFO-MAC employs an optimal compressor tree structure and utilizes integer linear programming (ILP) to refine the stage assignment and interconnection of the compressors. Additionally, it explicitly exploits the non-uniform arrival time profile of the carry propagate adder (CPA) within multipliers to achieve targeted optimization. Moreover, the framework also supports the optimization of fused MAC architectures. Experimental results demonstrate that multipliers and MACs optimized by UFO-MAC Pareto-dominate state-of-the-art baselines and commercial IP libraries. The performance gain of UFO-MAC is further validated through the implementation of multipliers and MACs within functional modules, underlining its efficacy in real scenarios.

We exhibit that, when given a classical Byzantine agreement protocol designed in the private-channel model, it is feasible to construct a quantum agreement protocol that can effectively handle a full-information adversary. Notably, both protocols have equivalent levels of resilience, round complexity, and communication complexity. In the classical private-channel scenario, participating players are limited to exchanging classical bits, with the adversary lacking knowledge of the exchanged messages. In contrast, in the quantum full-information setting, participating players can exchange qubits, while the adversary possesses comprehensive and accurate visibility into the system's state and messages. By showcasing the reduction from quantum to classical frameworks, this paper demonstrates the strength and flexibility of quantum protocols in addressing security challenges posed by adversaries with increased visibility. It underscores the potential of leveraging quantum principles to improve security measures without compromising on efficiency or resilience. By applying our reduction, we demonstrate quantum advantages in the round complexity of asynchronous Byzantine agreement protocols in the full-information model. It is well known that in the full-information model, any classical protocol requires $Ω(n)$ rounds to solve Byzantine agreement with probability one even against Fail-stop adversary when resilience $t=Θ(n)$. We show that quantum protocols can achieve $O(1)$ rounds (i) with resilience $t0$, therefore surpassing the classical lower bound.

It has been shown recently that the framework of quantum sampling, as introduced by Bouman and Fehr, can lead to new entropic uncertainty relations highly applicable to finite-key cryptographic analyses. Here we revisit these so-called sampling-based entropic uncertainty relations, deriving newer, more powerful, relations and applying them to source-independent quantum random number generators and high-dimensional quantum key distribution protocols. Along the way, we prove several interesting results in the asymptotic case for our entropic uncertainty relations. These sampling-based approaches to entropic uncertainty, and their application to quantum cryptography, hold great potential for deriving proofs of security for quantum cryptographic systems, and the approaches we use here may be applicable to an even wider range of scenarios.

Uyghur language is written in a modified Arabic script. Due to its cursive nature and the lack of enough labeled training samples, Uyghur document recognition is still a challenging problem. In this paper, we propose a new Recurrent Neural Network (RNN) based Uyghur text line recognition method combining Gated Recurrent Unit (GRU) and Restricted Boltzmann Machine (RBM) with pretraining mechanism. We also present a novel curriculum learning technique guided by sample distribution information. Experimental results on practical Uyghur printed document image dataset show that the proposed network architecture and training strategy not only achieve better recognition accuracy compared with traditional methods, but can accelerate the training speed as well.