Search

Applying large language models (LLMs) for academic API usage shows promise in reducing researchers' academic information seeking efforts. However, current LLM API-using methods struggle with complex API coupling commonly encountered in academic queries. To address this, we introduce SoAy, a solution-based LLM API-using methodology for academic information seeking. It uses code with a solution as the reasoning method, where a solution is a pre-constructed API calling sequence. The addition of the solution reduces the difficulty for the model to understand the complex relationships between APIs. Code improves the efficiency of reasoning. To evaluate SoAy, we introduce SoAyBench, an evaluation benchmark accompanied by SoAyEval, built upon a cloned environment of APIs from AMiner. Experimental results demonstrate a 34.58-75.99\% performance improvement compared to state-of-the-art LLM API-based baselines. All datasets, codes, tuned models, and deployed online services are publicly accessible at https://github.com/RUCKBReasoning/SoAy., Comment: 22 pages, 13 figures

Number Theoretic Transform (NTT) is an essential mathematical tool for computing polynomial multiplication in promising lattice-based cryptography. However, costly division operations and complex data dependencies make efficient and flexible hardware design to be challenging, especially on resource-constrained edge devices. Existing approaches either focus on only limited parameter settings or impose substantial hardware overhead. In this paper, we introduce a hardware-algorithm methodology to efficiently accelerate NTT in various settings using in-cache computing. By leveraging an optimized bit-parallel modular multiplication and introducing costless shift operations, our proposed solution provides up to 29x higher throughput-per-area and 2.8-100x better throughput-per-area-per-joule compared to the state-of-the-art., Comment: This work is accepted to the 60th Design Automation Conference (DAC), 2023

In the age of big data, information security has become a major issue of debate, especially with the rise of the Internet of Things (IoT), where attackers can effortlessly obtain physical access to edge devices. The hash algorithm is the current foundation for data integrity and authentication. However, it is challenging to provide a high-performance, high-throughput, and energy-efficient solution on resource-constrained edge devices. In this paper, we propose Inhale, an in-SRAM architecture to effectively compute hash algorithms with innovative data alignment and efficient read/write strategies to implicitly execute data shift operations through the in-situ controller. We present two variations of Inhale: Inhale-Opt, which is optimized for latency, throughput, and area-overhead; and Inhale-Flex, which offers flexibility in repurposing a part of last-level caches for hash computation. We thoroughly evaluate our proposed architectures on both SRAM and ReRAM memories and compare them with the state-of-the-art in-memory and ASIC accelerators. Our performance evaluation confirms that Inhale can achieve 1.4x - 14.5x higher throughput-per-area and about two-orders-of-magnitude higher throughput-per-area-per-energy compared to the state-of-the-art solutions., Comment: 9 pages, ICCAD 2022

To provide data and code confidentiality and reduce the risk of information leak from memory or memory bus, computing systems are enhanced with encryption and decryption engine. Despite massive efforts in designing hardware enhancements for data and code protection, existing solutions incur significant performance overhead as the encryption/decryption is on the critical path. In this paper, we present Sealer, a high-performance and low-overhead in-SRAM memory encryption engine by exploiting the massive parallelism and bitline computational capability of SRAM subarrays. Sealer encrypts data before sending it off-chip and decrypts it upon receiving the memory blocks, thus, providing data confidentiality. Our proposed solution requires only minimal modifications to the existing SRAM peripheral circuitry. Sealer can achieve up to two orders of magnitude throughput-per-area improvement while consuming 3x less energy compared to the prior solutions., Comment: 6 pages, ISLPED 2022

The global attitude synchronization problem is studied for networked rigid bodies under directed topologies. To avoid the asynchronous pitfall where only vector parts converge to some identical value but scalar parts do not, multiplicative quaternion errors are leveraged to develop attitude synchronization protocols for rigid bodies with the absolute measurements. It is shown that global synchronization of networked rigid bodies can be achieved if and only if the directed topology is quasi-strongly connected. Simultaneously, a novel double-energy-function analysis method, equipped with an ordering permutation technique about scalar parts and a coordinate transformation mechanism, is constructed for the quaternion behavior analysis of networked rigid bodies. In particular, global synchronization is achieved with our analysis method regardless of the highly nonlinear and strongly coupling problems resulting from multiplicative quaternion errors, which seriously hinder the traditional analysis of global synchronization for networked rigid bodies. Simulations for networked spacecraft are presented to show the global synchronization performances under different directed topologies., Comment: 26 pages, 6 figures

Generally, the classic iterative learning control (ILC) methods focus on finding design conditions for repetitive systems to achieve the perfect tracking of any specified trajectory, whereas they ignore a fundamental problem of ILC: whether the specified trajectory is trackable, or equivalently, whether there exist some inputs for the repetitive systems under consideration to generate the specified trajectory? The current paper contributes to dealing with this problem. Not only is a concept of trackability introduced formally for any specified trajectory in ILC, but also some related trackability criteria are established. Further, the relation between the trackability and the perfect tracking tasks for ILC is bridged, based on which a new convergence analysis approach is developed for ILC by leveraging properties of a functional Cauchy sequence (FCS). Simulation examples are given to verify the effectiveness of the presented trackability criteria and FCS-induced convergence analysis method for ILC., Comment: Submitted

This paper presents an efficient approach for the conceptual design of architectural surfaces which are composed of triangular panels. In the free-form design of discrete architectural surfaces, the Gaussian curvature plays an important role not only aesthetically but also in terms of stiffness and constructability. However, designing a surface manually with specific Gaussian curvatures can be a time-consuming task. We propose a method to find a triangulated surface with user-specified Gaussian curvatures (not limited to constant Gaussian curvatures) and boundary vertex positions. In addition, the conformal class of the final design can be specified; that is, the user has control over the shape (the corner angles) of each triangular panel. The panels could be encouraged to form a regular tessellation or kept close to those of the initial design. The controllability of the conformal class suppresses possible distortion of the panels, resulting in higher structural performance and aesthetics. Our method relies on the idea in computational conformal geometry called circle packing. In this line of research, the discrete Ricci flow has been widely used for surface modelling. However, it is not trivial to incorporate constraints such as boundary locations and convexity of the spanned surface, which are essential to architectural applications. We propose a perturbation of the discrete Ricci energy and develop a least-squares-based optimisation scheme to address these problems with an open-source implementation available online.

Question answering is an effective method for obtaining information from knowledge bases (KB). In this paper, we propose the Neural-Symbolic Complex Question Answering (NS-CQA) model, a data-efficient reinforcement learning framework for complex question answering by using only a modest number of training samples. Our framework consists of a neural generator and a symbolic executor that, respectively, transforms a natural-language question into a sequence of primitive actions, and executes them over the knowledge base to compute the answer. We carefully formulate a set of primitive symbolic actions that allows us to not only simplify our neural network design but also accelerate model convergence. To reduce search space, we employ the copy and masking mechanisms in our encoder-decoder architecture to drastically reduce the decoder output vocabulary and improve model generalizability. We equip our model with a memory buffer that stores high-reward promising programs. Besides, we propose an adaptive reward function. By comparing the generated trial with the trials stored in the memory buffer, we derive the curriculum-guided reward bonus, i.e., the proximity and the novelty. To mitigate the sparse reward problem, we combine the adaptive reward and the reward bonus, reshaping the sparse reward into dense feedback. Also, we encourage the model to generate new trials to avoid imitating the spurious trials while making the model remember the past high-reward trials to improve data efficiency. Our NS-CQA model is evaluated on two datasets: CQA, a recent large-scale complex question answering dataset, and WebQuestionsSP, a multi-hop question answering dataset. On both datasets, our model outperforms the state-of-the-art models. Notably, on CQA, NS-CQA performs well on questions with higher complexity, while only using approximately 1% of the total training samples., Comment: 18 pages, 4 figures, published in JWS

For iterative learning control (ILC), one of the basic problems left to address is how to solve the contradiction between convergence conditions for the output tracking error and for the input signal (or error). This problem is considered in the current paper, where the robust convergence analysis is achieved for ILC systems in the presence of nonrepetitive uncertainties. A system equivalence transformation (SET) is proposed for ILC such that given any desired reference trajectories, the output tracking problems for general nonsquare multi-input, multi-output (MIMO) systems can be equivalently transformed into those for the specific class of square MIMO systems with the same input and output channels. As a benefit of SET, a unified condition is only needed to guarantee both the uniform boundedness of all system signals and the robust convergence of the output tracking error, which avoids causing the condition contradiction problem in implementing the double-dynamics analysis approach to ILC. Simulation examples are included to demonstrate the validity of our established robust ILC results., Comment: Submitted

Learning to perform perfect tracking tasks based on measurement data is desirable in the controller design of systems operating repetitively. This motivates the present paper to seek an optimization-based design approach for iterative learning control (ILC) of repetitive systems with unknown nonlinear time-varying dynamics. It is shown that perfect output tracking can be realized with updating inputs, where no explicit model knowledge but only measured input/output data are leveraged. In particular, adaptive updating strategies are proposed to obtain parameter estimations of nonlinearities. A double-dynamics analysis approach is applied to establish ILC convergence, together with boundedness of input, output, and estimated parameters, which benefits from employing properties of nonnegative matrices. Moreover, robust convergence is explored for optimization-based adaptive ILC in the presence of nonrepetitive uncertainties. Simulation tests are also implemented to verify the validity of our optimization-based adaptive ILC., Comment: Submitted