====== Programming Assignment II======
Select one of the assignments below.
Assignments marked with {{:courses:xai:winner.png?25|}} can be extended as a continution in Programming Assgnment II.
Projects marked with {{:courses:xai:contract.png?25|}} can be (with some additional work and depending on the results) published as scientific papers.

===== ACFXon OPTUNA  =====
{{:courses:xai:winner.png?30|}}
{{:courses:xai:contract.png?30|}}

The goal is to run hyperparameter optimization algorithm such as optuna, collect results from it and use [[https://github.com/sbobek/acfx|ACFX]] to try to explain the impact of different hyperparameters on the quality of the optimization process

===== PPCF Counterfactual explainer evaluation  =====
{{:courses:xai:winner.png?30|}}
{{:courses:xai:contract.png?30|}}

The goal is to take: https://github.com/ofurman/counterfactuals/tree/main and evaluate it on more examples

===== Multi-modal explanations  =====
{{:courses:xai:winner.png?30|}}
{{:courses:xai:contract.png?30|}}

The goal is to use LLAVA/Molmo/NVLM/LLama/VALE to build explanations for image classification.


===== Xai and GenAI  =====
{{:courses:xai:winner.png?30|}}
{{:courses:xai:contract.png?30|}}

The goal is to use for instance [[https://github.com/JoaoLages/diffusers-interpret|Diffusers-Interpret]] to generate explanations for generative AI (images, other team text)



===== Alpha Evolve =====
{{:courses:xai:winner.png?30|}}
{{:courses:xai:contract.png?30|}}
Try to setup and raun exmaple from AlphaEvolve public implementation: https://arxiv.org/abs/2506.13131


===== Run and compare different XAI methos on anomaly detection task =====
{{:courses:xai:winner.png?30|}}
{{:courses:xai:contract.png?30|}}

Focus on rule-based explainers, but also SAHP and LIME: calculate output for anomaly detection task (e.g.: https://zenodo.org/records/11469702) and analyze results