Výsledky vyhledávání - Programming Exercise Generation Benchmark*

  • Zobrazuji výsledky 1 - 9 z 9
Upřesnit hledání
  1. 1

    A Survey Study on the State of the Art of Programming Exercise Generation Using Large Language Models Autor Frankford, Eduard, Hohn, Ingo, Sauerwein, Clemens, Breu, Ruth

    ISSN: 2377-570X
    Vydáno: IEEE 29.07.2024
    “…This paper analyzes Large Language Models (LLMs) with regard to their programming exercise generation capabilities…”
    Získat plný text
    Konferenční příspěvek
  2. 2

    Modelling Efficiency of Electric Utilities Using Three Stage Virtual Frontier Data Envelopment Analysis with Variable Selection by Loads Method Autor Kannan, Pavala Malar, Marthandan, Govindan, Kannan, Rathimala

    ISSN: 1996-1073, 1996-1073
    Vydáno: Basel MDPI AG 01.06.2021
    Vydáno v Energies (Basel) (01.06.2021)
    “… Therefore, benchmarking exercises allow policy makers and regulators to gauge the relative efficiency of electric utilities and help them to reward or penalize the electric utilities accordingly…”
    Získat plný text
    Journal Article
  3. 3

    Dataset of Program Source Codes Solving Unique Programming Exercises Generated by Digital Teaching Assistant Autor Demidova, Liliya A., Andrianova, Elena G., Sovietov, Peter N., Gorchakov, Artyom V.

    ISSN: 2306-5729, 2306-5729
    Vydáno: Basel MDPI AG 01.06.2023
    Vydáno v Data (Basel) (01.06.2023)
    “…This paper presents a dataset containing automatically collected source codes solving unique programming exercises of different types…”
    Získat plný text
    Journal Article
  4. 4

    Programming and execution models for parallel bounded exhaustive testing Autor Awar, Nader Al, Jain, Kush, Rossbach, Christopher J., Gligoric, Milos

    ISSN: 2475-1421, 2475-1421
    Vydáno: 01.10.2021
    “… We present the first programming and execution models, dubbed Tempo, for parallel exploration of hybrid test generation programs…”
    Získat plný text
    Journal Article
  5. 5

    A Track-Based Conference Scheduling Problem Autor Riquelme, Fabian, Montero, Elizabeth, Pérez-Cáceres, Leslie, Rojas-Morales, Nicolás

    ISSN: 2227-7390, 2227-7390
    Vydáno: Basel MDPI AG 01.11.2022
    Vydáno v Mathematics (Basel) (01.11.2022)
    “…: literature review, problem formulation and benchmarking, and heuristic approach. We provide a literature review of conference scheduling approaches that organizes these approaches within a timetabling problem taxonomy…”
    Získat plný text
    Journal Article
  6. 6

    Inferring test models from user bug reports using multi-objective search Autor Guizzo, Giovani, Califano, Francesco, Sarro, Federica, Ferrucci, Filomena, Harman, Mark

    ISSN: 1382-3256, 1573-7616, 1573-7616
    Vydáno: New York Springer US 01.07.2023
    “… These FSMs can then be used by testers to both exercise the reported bugs and create tests that can potentially reveal new bugs…”
    Získat plný text
    Journal Article
  7. 7

    Generation of variational standard plant room solutions Autor Medjdoub, Benachir, Richens, Paul, Barnard, Nick

    ISSN: 0926-5805
    Vydáno: Amsterdam Elsevier B.V 01.03.2003
    Vydáno v Automation in construction (01.03.2003)
    “…We have used the object-based CAD programming to take advantage of standardisation to handle the selection, sizing, layout and (potentially…”
    Získat plný text
    Journal Article
  8. 8

    Tools and techniques for efficient parallelization on modern parallel microprocessors Autor Vadlamani, Srinivas

    ISBN: 9780549256991, 0549256997
    Vydáno: ProQuest Dissertations & Theses 01.01.2007
    “…Lately, focus in processor design has shifted from improving single thread program performance, traditionally achieved by improving branch prediction,…”
    Získat plný text
    Dissertation
  9. 9

    Evaluating and Aligning CodeLLMs on Human Preference Autor Yang, Jian, Yang, Jiaxi, Jin, Ke, Miao, Yibo, Zhang, Lei, Yang, Liqun, Cui, Zeyu, Zhang, Yichang, Binyuan Hui, Lin, Junyang

    ISSN: 2331-8422
    Vydáno: Ithaca Cornell University Library, arXiv.org 06.12.2024
    Vydáno v arXiv.org (06.12.2024)
    “… Most previous code-related benchmarks, which consist of various programming exercises along with the corresponding test cases, are used as a common measure to evaluate the performance and capabilities of code LLMs…”
    Získat plný text
    Paper