MAC5913 - Inteligência artificial generativa para engenharia de software (2025)

Perfilado de sección

• Seleccionar sección General

  General

  Colapsar todo Expandir todo

  • Seleccionar actividad Avisos

    

    Avisos Foro
  • Seleccionar actividad Informações gerais

    

    Informações gerais Página
  • Seleccionar actividad Repositório de notebooks

    

    Repositório de notebooks URL
  • Seleccionar actividad Discussões

    

    Discussões Foro
• Seleccionar sección Introdução à IA e aprendizado de máquina

  Introdução à IA e aprendizado de máquina

  • Seleccionar actividad Slides

    

    Slides Archivo
  • Seleccionar actividad Paper: Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond by Yang et al.

    

    Paper: Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond by Yang et al. Archivo
  • Seleccionar actividad Tokenizador da OpenAI

    

    Tokenizador da OpenAI URL
• Seleccionar sección Arquitetura de transformadores

  Arquitetura de transformadores

  • Seleccionar actividad Slides

    

    Slides Archivo
  • Seleccionar actividad Notebook: visualização

    

    Notebook: visualização URL
  • Seleccionar actividad Notebook: fine-tuning para detecção de vulnerabilidades

    

    Notebook: fine-tuning para detecção de vulnerabilidades URL
  • Seleccionar actividad Paper: Attention is all you need by Vaswani et al.

    

    Paper: Attention is all you need by Vaswani et al. URL
• Seleccionar sección Inteligência artificial generativa e engenharia de prompts

  Inteligência artificial generativa e engenharia de prompts

  • Seleccionar actividad Slides

    

    Slides Archivo
  • Seleccionar actividad Paper: A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT by White et al.

    

    Paper: A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT by White et al. URL
  • Seleccionar actividad Paper: ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design by White et al.

    

    Paper: ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design by White et al. URL
  • Seleccionar actividad Paper: ReAct: Synergizing Reasoning and Acting in Language Models by Yao et al.

    

    Paper: ReAct: Synergizing Reasoning and Acting in Language Models by Yao et al. URL
• Seleccionar sección Estratégias de aprendizado em contexto

  Estratégias de aprendizado em contexto

  • Seleccionar actividad Slides

    

    Slides Archivo
  • Seleccionar actividad Paper: ThinkRepair: Self-Directed Automated Program Repair by Yin et al.

    

    Paper: ThinkRepair: Self-Directed Automated Program Repair by Yin et al. URL
  • Seleccionar actividad Paper: Test-Case-Driven Programming Understanding in Large Language Models for Better Code Generation by Tian et al.

    

    Paper: Test-Case-Driven Programming Understanding in Large Language Models for Better Code Generation by Tian et al. URL
• Seleccionar sección RAG

  RAG

  • Seleccionar actividad Slides

    

    Slides Archivo
  • Seleccionar actividad Notebook: RAG para usar uma API

    

    Notebook: RAG para usar uma API URL
  • Seleccionar actividad Paper: ChatGPT Inaccuracy Mitigation during Technical Report Understanding: Are We There Yet? by Tamanna et al.

    

    Paper: ChatGPT Inaccuracy Mitigation during Technical Report Understanding: Are We There Yet? by Tamanna et al. URL
• Seleccionar sección Análise (Reasoning) e atuação

  Análise (Reasoning) e atuação

  • Seleccionar actividad Slides

    

    Slides Archivo
  • Seleccionar actividad Notebook: Function calling para obter informações do Git

    

    Notebook: Function calling para obter informações do Git URL
• Seleccionar sección Limitações, futuro e conclusões

  Limitações, futuro e conclusões

  • Seleccionar actividad Slides

    

    Slides Archivo
  • Seleccionar actividad Paper: GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models by Mizardeh et al.

    

    Paper: GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models by Mizardeh et al. URL
  • Seleccionar actividad Paper: Role play with large language models by Shanahan et al.

    

    Paper: Role play with large language models by Shanahan et al. URL
  • Seleccionar actividad Paper: DAnTE: A Taxonomy for the Automation Degree of Software Engineering Tasks by Melegati & Guerra

    

    Paper: DAnTE: A Taxonomy for the Automation Degree of Software Engineering Tasks by Melegati & Guerra URL
• Seleccionar sección Projeto

  Projeto

  • Seleccionar actividad Escolha do grupo

    

    Escolha do grupo Elección de grupo

    No disponible hasta que: se pertenezca a cualquier grupo
  • Seleccionar actividad Projeto final

    

    Projeto final Tarea
  • Seleccionar actividad Avaliação pelos pares

    

    Avaliação pelos pares Cuestionario
  • Seleccionar actividad Fotos e vídeos do curso

    

    Fotos e vídeos do curso Tarea
  • Seleccionar actividad Todos os posters

    

    Todos os posters Carpeta