Suchergebnisse - coding (algorithm OR (algorithmics OR algorithmicsics))

Accelerating high-order continuum kinetic plasma simulations using multiple GPUs von Ho, Andrew, Vogman, Genia

Inhaltsangabe: “… are then used to inform and evaluate the design of performance portable algorithms for a multiple graphics …”
Volltext

GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration von Li, Xin, Chu, Qizhi, Chen, Yubin, Liu, Yang, Liu, Yaoqi, Yu, Zekai, Chen, Weize, Qian, Chen, Shi, Chuan, Yang, Cheng

Inhaltsangabe: “… algorithms via programming to generate solutions, and in case the coding agent does not work, the reasoning …”
Volltext

When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair von Luo, Wenqiang, Keung, Jacky Wai, Yang, Boyang, Ye, He, Goues, Claire Le, Bissyande, Tegawende F., Tian, Haoye, Le, Bach

Inhaltsangabe: “… fixing. However, LLM-based APR heavily relies on high-quality code repositories. A larger portion …”
Volltext

Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval von Pang, Ming, Yuan, Chunyuan, He, Xiaoyu, Fang, Zheng, Xie, Donghao, Qu, Fanyi, Jiang, Xue, Peng, Changping, Lin, Zhangang, Law, Ching, Shao, Jingping

Inhaltsangabe: “… numerous attributes, these algorithms generate a large number of identifiers, making it difficult to assess …”
Volltext

Generalized Restart Mechanism for Successive-Cancellation Flip Decoding of Polar Codes von Sagitov, Ilshat, Pillet, Charles, Balatsoukas-Stimming, Alexios, Giard, Pascal

Inhaltsangabe: “… Polar codes are a class of linear error-correction codes that have received a lot of attention due …”
Volltext

Design and Application of Multimodal Large Language Model Based System for End to End Automation of Accident Dataset Generation von Chowdhury, MD Thamed Bin Zaman, Hossain, Moazzem

Inhaltsangabe: “… consists of four components: automated web scraping code generation, news collection from online sources …”
Volltext

Rewriting Pre-Training Data Boosts LLM Performance in Math and Code von Fujii, Kazuki, Tajima, Yukito, Mizuki, Sakae, Kawamura, Masaki, Shimada, Hinari, Shiotani, Taihei, Saito, Koshiro, Oi, Masanari, Nakamura, Taishi, Okamoto, Takumi, Ishida, Shigeki, Hattori, Kakeru, Ma, Youmi, Takamura, Hiroya, Yokota, Rio, Sakuma, Jun, Okazaki, Naoaki

Inhaltsangabe: “… into self-contained, algorithmically efficient examples. Unlike prior methods that rely on exclusionary …”
Volltext

Hallucination to Consensus: Multi-Agent LLMs for End-to-End JUnit Test Generation von Xu, Qinghua, Wang, Guancheng, Briand, Lionel, Liu, Kui

Inhaltsangabe: “… for automated approaches. Traditional methods primarily rely on search-based or randomized algorithms to achieve …”
Volltext

Efficient dataset construction using active learning and uncertainty-aware neural networks for plasma turbulent transport surrogate models von Ho, Aaron, Zanisi, Lorenzo, de Leeuw, Bram, Galvan, Vincent, Rodriguez-Fernandez, Pablo, Howard, Nathaniel T.

Inhaltsangabe: “… as a proxy for more expensive codes, such as CGYRO or GENE. The newly implemented algorithm uses …”
Volltext

Reversible Video Steganography Using Quick Response Codes and Modified ElGamal Cryptosystem von Mstafa, Ramadhan J.

Inhaltsangabe: “… the modified ElGamal algorithm to encrypt secret QR codes. Concurrently, it applies two-dimensional DWT …”
Volltext

Trace-Based Reconstruction of Quantum Circuit Dataflow in Surface Codes von Trochatos, Theodoros, Kang, Christopher, Wang, Andrew, Chong, Frederic T., Szefer, Jakub

Inhaltsangabe: “… correction. A promising quantum error-correcting code for large-scale quantum computing is the surface code …”
Volltext

ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation von Ye, Kai, Su, Liangcai, Qian, Chenxiong

Inhaltsangabe: “… and algorithmic logic often results in functional deficiencies and security vulnerabilities in generated code …”
Volltext

LLM Priors for ERM over Programs von Singhal, Shivam, Mishra, Priyadarsi, Malach, Eran, Galanti, Tomer

Inhaltsangabe: “… piece of ``Python code''), it can be learned from relatively few examples by performing ERM over …”
Volltext

Error-structure-tailored early fault-tolerant quantum computing von Zeng, Pei, Zheng, Guo, Xu, Qian, Jiang, Liang

Inhaltsangabe: “… prohibitively large. A critical challenge arises in many quantum algorithms with Clifford + $φ$ compiling, where …”
Volltext

HPRMAT: A high-performance R-matrix solver with GPU acceleration for coupled-channel problems in nuclear physics von Lei, Jin

Inhaltsangabe: “… for the linear algebra routines in existing R-matrix codes, HPRMAT employs direct linear equation solving …”
Volltext

Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch von Ferreira, Fabio, Wobbe, Lucca, Krishnakumar, Arjun, Hutter, Frank, Zela, Arber

Inhaltsangabe: “… code directly. We use it as a testbed to compare classical HPO algorithms against LLM-based methods …”
Volltext

QASM-Eval: A Dataset to Train and Evaluate LLMs on OpenQASM-3 Beyond Quantum Circuits von Fu, Zhenxiao, Jiang, Lei, Chen, Fan

Inhaltsangabe: “… in code generation, there is still no dataset specifically designed to train and evaluate LLMs on OpenQASM …”
Volltext

Detecting and Reacting to Data-Drift in Streaming Optimisation Domains - Code and Data von Anonymous

Inhaltsangabe: “… <p>This repository contains the code and data for reproducibility of the paper 'Detecting …”
Volltext

HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark von Li, Chaojian, Yu, Zhongzhi, Fu, Yonggan, Zhang, Yongan, Zhao, Yang, You, Haoran, Yu, Qixuan, Wang, Yue, Lin, Yingyan Celine

Inhaltsangabe: “… -disciplinary knowledge in the algorithm, micro-architecture, and device-specific compilation. First …”
Volltext

Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings von Hammouamri, Ilyass, Khalfaoui-Hassani, Ismail, Masquelier, Timothée

Inhaltsangabe: “… the expressivity in SNNs. Yet, efficient algorithms to learn these delays have been lacking. Here, we propose a new …”
Volltext