Model Selection + Research Link

[YounesBensafia]

Files to create and modify

Create:

• docs/model_selection.md: Document when to use each model family (classical ML, transformers, diffusion, GNNs)
• research/classical_ml.md: Summarize classical ML use cases and examples
• research/transformers.md: Summarize transformer-based applications in language, vision, and multimodal tasks
• research/diffusion_models.md: Summarize diffusion models and when they outperform GANs
• research/graph_neural_networks.md: Summarize graph neural networks and their use cases
• research/research_interpretation.md: Guidelines for interpreting research papers for each model family

Acceptance Criteria

• Document clearly explains when classical ML is still effective
• Transformer dominance in language, vision, and multimodal tasks is summarized
• Diffusion models’ advantages over GANs are detailed
• Graph neural network use cases are identified
• Guidelines for interpreting research surrounding each model family are provided
• All documentation is accessible, formatted for easy review, and structured for reference