Results 121 to 130 of about 4,724 (255)

Condor: A Code Discriminator Integrating General Semantics With Code Details

IEEE Transactions on Software Engineering
LLMs demonstrate significant potential across various software engineering tasks. However, they still face challenges in generating correct code on the first attempt when addressing complex requirements. Introducing a discriminator to select reliable outputs from multiple generated results is an effective way to enhance their reliability and stability.
Qingyuan Liang, Zhao Zhang, Chen Liu 0041, Zeyu Sun 0004, Wenjie Zhang 0007, Yizhou Chen, Zixiao Zhao, Qi Luo, Wentao Wang, Yanjie Jiang, Yingfei Xiong 0001, Lu Zhang 0023   +11 more
openaire   +2 more sources

GraphRAG for engineering diagrams: ChatP&ID enables LLM interaction with P&IDs

AIChE Journal, EarlyView.
Abstract Piping and Instrumentation Diagrams (P&IDs) are central to process engineering workflows, yet extracting information from them remains a tedious and time‐consuming task. This work introduces ChatP&ID, a framework enabling natural‐language interaction with smart P&IDs through Graph Retrieval‐Augmented Generation (GraphRAG), to our knowledge ...
Achmad Anggawirya Alimin, Artur M. Schweidtmann   +1 more
wiley   +1 more source

Latent semantic learning by efficient sparse coding with hypergraph regularization

, 2011
This paper presents a novel latent semantic learning algorithm for action recognition. Through efficient sparse coding, we can learn latent semantics (i.e. high-level features) from a large vocabulary of abundant mid-level features (i.e. visual keywords).
Lu, Zhiwu, Peng, Yuxin
core   +1 more source

The Necessity of Dynamic Workflow Managers for Advancing Self‐Driving Labs and Optimizers

Advanced Intelligent Discovery, EarlyView.
We assess the maturity and integration readiness of key methodologies for Materials Acceleration Platforms, highlighting the need for dynamic workflow managers. Demonstrating this, we integrate PerQueue into a color‐mixing robot, showing how flexible orchestration improves coordination and optimization.
Simon K. Steensen, Patrick W. V. Butler, Jesper R. Pedersen, Nis Fisker‐Bødker, Tejs Vegge, Jin Hyun Chang, Ivano E. Castelli   +6 more
wiley   +1 more source

Large Language Model in Materials Science: Roles, Challenges, and Strategic Outlook

Advanced Intelligent Discovery, EarlyView.
Large language models (LLMs) are reshaping materials science. Acting as Oracle, Surrogate, Quant, and Arbiter, they now extract knowledge, predict properties, gauge risk, and steer decisions within a traceable loop. Overcoming data heterogeneity, hallucinations, and poor interpretability demands domain‐adapted models, cross‐modal data standards, and ...
Jinglan Zhang, Xinyi Chen, Xu Ye, Yulin Yang, Bin Ai   +4 more
wiley   +1 more source

Parametic coding of audio objects: technology, performance and opportunities

, 2022
S.149-158While efficient low-bitrate coding of multi-channel audio (surround sound) has been an active topic of research for about one decade, the quest for representing audio signals in a semantically more relevant way has recently led to the ...
Terentiv, L., Herre, J.
core  

Semantic Channel Coding

Abstract In this chapter, we investigate the semantic channel coding. First, we introduce the jointly asymptotic equipartition property (JAEP) in the semantic sense and define the jointly synonymous typical set. Then we prove the semantic channel coding theorem by using the jointly typical decoding over the jointly synonymous typical set ...
Kai Niu, Ping Zhang
openaire   +1 more source

Smart Flexible Tactile Sensors: Recent Progress in Device Designs, Intelligent Algorithms, and Multidisciplinary Applications

Advanced Intelligent Discovery, EarlyView.
Flexible tactile sensors have considerable potential for broad application in healthcare monitoring, human–machine interfaces, and bioinspired robotics. This review explores recent progress in device design, performance optimization, and intelligent applications. It highlights how AI algorithms enhance environmental adaptability and perception accuracy
Siyuan Wang, Ming Dong, Rongrong Bao, Caofeng Pan   +3 more
wiley   +1 more source

Advanced fine-tuning procedures to enhance DNN robustness in visual coding for machines

EURASIP Journal on Image and Video Processing
Video Coding for Machines (VCM) is gaining momentum in applications like autonomous driving, industry manufacturing, and surveillance, where the robustness of machine learning algorithms against coding artifacts is one of the key success factors.
Alban Marie, Karol Desnos, Alexandre Mercat, Luce Morin, Jarno Vanne, Lu Zhang   +5 more
doaj   +1 more source

Computer Vision Pipeline for Image Analysis for Freeze‐Fracture Electron Microscopy: Rosette Cellulose Synthase Complexes Case

Advanced Intelligent Discovery, EarlyView.
This paper presents a computer vision (deep learning) pipeline integrating YOLOv8 and YOLOv9 for automated detection, segmentation, and analysis of rosette cellulose synthase complexes in freeze‐fracture electron microscopy images. The study explores curated dataset expansion for model improvement and highlights pipeline accuracy, speed ...
Siri Mudunuri, Leala Carbonneau, Eric M. Roberts, Alison W. Roberts, Candace H. Haigler, Alexey V. Gulyuk, Yaroslava G. Yingling   +6 more
wiley   +1 more source