Automatically generating scientific literature surveys is a valuable task that can significantly enhance research efficiency. However, the diverse and complex nature of information within a literature survey poses sub...
详细信息
ISBN:
(纸本)9789819794423;9789819794430
Automatically generating scientific literature surveys is a valuable task that can significantly enhance research efficiency. However, the diverse and complex nature of information within a literature survey poses substantial challenges for generative models. In this paper, we design a series of prompts to systematically leverage large language models (LLMs), enabling the creation of comprehensive literature surveys through a step-by-step approach. Specifically, we design prompts to guide LLMs to sequentially generate the title, abstract, hierarchical headings, and the main content of the literature survey. We argue that this design enables the generation of the headings from a high-level perspective. During the content generation process, this design effectively harnesses relevant information while minimizing costs by restricting the length of both input and output content in LLM queries. Our implementation with Qwen-long achieved third place in the NLPCC 2024 Scientific Literature Survey Generation evaluation task, with an overall score only 0.03% lower than the second-place team. Additionally, our soft heading recall is 95.84%, the second best among the submissions. Thanks to the efficient prompt design and the low cost of the Qwen-long API, our method reduces the expense for generating each literature survey to 0.1 RMB, enhancing the practical value of our method.
This research aims to explore the automation design principles, technical architecture and application process of electrical control systems in industrial production. This paper evaluates the impact of automation desi...
详细信息
Pottery design has traditionally been a manual and intricate process, often constrained by physical limitations. This paper introduces PM4Pottery, a groundbreaking scriptable parametric modeling interface specifically...
详细信息
Exploiting a weakness in OpenSSL's TLS protocol implementation, the Heartbleed vulnerability was found in April 2014 and exposed sensitive data. This study describes a co-processor architecture that reduces the da...
详细信息
To support technical trend of multi-die integration in HPC platform, various die-to-die interface IPs have been introduced for seamless connection between dies with the wide bandwidth. In addition to the conventional ...
详细信息
ISBN:
(纸本)9798350334982
To support technical trend of multi-die integration in HPC platform, various die-to-die interface IPs have been introduced for seamless connection between dies with the wide bandwidth. In addition to the conventional channel routed in single medium of Si-interposer or organic substrate, D2D interface through the channel where multiple media are used may also be required depending on the system requirements. This study focuses on analyzing and comparing the bandwidth of D2D interface in various channel configurations including the traditional solutions with a single medium. The entire channel structure consists of a multi-stage channel that connects two interposers with a SOC die and multiple HBM dies in an organic substrate, or two small ABF packages in a large-size, low-cost HDI substrate. In the entire D2D channel with multiple media, impedance mismatching and coupling may occur additionally at the joint balls and the performance degradation of high-speed signal is inevitable, but the performance can be improved throughdesign optimization process. The channel performance with 9 type configurations was assessed and the allowable signaling speed was estimated by the target criteria of eye opening. By each channel configuration, it was suggested which design characteristics are dominant to the signal performance and how the performance can be improved. In conclusion, by comparing and analyzing the signal performance depending on complex design parameters in various channel conditions, we suggested the optimal D2D design solution for multi-die integration, considering target bandwidth and package cost. This approach is expected to be useful to comprehend the performance of multi-stage channel consisting of multiple joint junctions with uneven characteristic impedance.
In the contemporary era of digital transformation, the prevalence of multi-campus universities is escalating. This progression necessitates standardized yet adaptable course designs suitable for deployment across dive...
详细信息
ISBN:
(纸本)9798350394023;9798350394030
In the contemporary era of digital transformation, the prevalence of multi-campus universities is escalating. This progression necessitates standardized yet adaptable course designs suitable for deployment across diverse campuses. The overarching challenge encompasses the formulation of courses with uniform objectives and quality, while simultaneously respecting the distinct attributes and limitations of each campus. The Norwegian University of Science and Technology (NTNU), after its merger with three state colleges, confronted with these complexities, leading to the inception of a wide array of courses spread across multiple campuses. To address this multifaceted scenario, our research introduced a gamified tool designed to simplify the multi-campus course designprocess. This tool, built on principles of cohesion, alignment, and adaptability, ensures the catering of unique campus-specific requirements. We gauged the tool's effectiveness through workshops with educators, which highlighted its capacity to instill structured course design methodologies, strengthen collaboration, and elevate awareness among educators about multi-campus nuances. Notable feedback from educators emphasized the potential advantages of digitizing this tool. A digital adaptation would not only enhance integration with existing learning management systems but also offer the versatility of synchronous and asynchronous collaborative course design, eliminating geographical constraints. This research, therefore, provides an innovative, gamified solution adept for universities worldwide, aiming to surmount similar multi-campus design challenges.
The shape, material property, and part quality transformation capabilities of a manufacturing process are essential process capability knowledge that are traditionally acquired by process planners through experience. ...
详细信息
The shape, material property, and part quality transformation capabilities of a manufacturing process are essential process capability knowledge that are traditionally acquired by process planners through experience. While efforts have been made over the years to develop automated systems that utilize known process capabilities for process selection and manufacturability assessment of part designs, such systems are hampered by the lack of a systematic approach to capture and model the shape, material property, and part quality transformation capabilities from design and manufacturing data. In this paper, the shape transformation capabilities of representative machining operations are modeled using 3D Variational Autoencoders and Generative Adversarial Networks (3D-VAE-GANs.) The proposed approach models the shape transformation capability as a latent probability distribution from which visualizations of realistic machinable features can be sampled for shape decomposition and reconstruction, thereby assisting machining process selection by a process planner and manufacturability assessment of part shapes generated by a designer. (C) 2022 Society of Manufacturing Engineers (SME). Published by Elsevier Ltd. All rights reserved. Peer-review under responsibility of the Scientific Committee of the NAMRI/SME.
The process of De Novo drug design involves the integration of artificial intelligence with computational intelligence techniques. The proposed system aims to provide precision therapeutics through the development of ...
详细信息
The widespread integration of Machine Learning (ML) in software systems has brought forth unprecedented advancements, yet the surge in energy consumption raises ecological concerns. This research addresses the environ...
详细信息
ISBN:
(纸本)9798400705915
The widespread integration of Machine Learning (ML) in software systems has brought forth unprecedented advancements, yet the surge in energy consumption raises ecological concerns. This research addresses the environmental impact of ML development, focusing on the energy implications of design decisions in ML-based systems. This thesis aims to offer insights into the energy consumption patterns influenced by deployment architecture and training environment. Different case studies on ML-based systems will be conducted to validate and demonstrate the implications of these design choices. The expected outcomes encompass actionable insights, validated through rigorous evaluations, and the development of an energy prediction tool for ML-based system development, to help in the decision-making process. This work contributes to the broader field of Green AI by addressing a critical gap and guiding the transition towards a more sustainable AI landscape.
This paper introduces "PARAMETERS", a serious game implementation, as a novel pedagogical tool for enhancing game design and balancing education within higher education settings, specifically in game develop...
详细信息
ISBN:
(纸本)9798350374537;9798350374544
This paper introduces "PARAMETERS", a serious game implementation, as a novel pedagogical tool for enhancing game design and balancing education within higher education settings, specifically in game development courses. Recognizing the complexity and educational value of game balancing-a process crucial for ensuring fairness, engagement, and replayability in games-this research aims to bridge the gap between theoretical knowledge and practical application in academic curricula. By integrating PARAMETERS into a game design curriculum, we examine its effectiveness in facilitating active learning and mastery of game design principles among students. Our methodology leverages PARAMETERS' simplified RPG mechanics, focusing on numerical interactions and stat management, to allow students hands-on experience with core game development tasks without the distractions of complex graphics or narratives. The outcomes of this integration, evaluated through a detailed case study, indicate a significant enhancement in students' comprehension of game balancing concepts and their application in real-world scenarios. Our study contributes to the discourse on game-based learning in technical education by demonstrating the pedagogical benefits of using serious games like PARAMETERS. It offers insights into effective strategies for embedding practical game design exercises into higher education, underscoring the potential of serious games to complement and enrich traditional learning approaches in this field of game development.
暂无评论