Dylan Slack

TalkToModel. TalkToModel gives anyone with the powers of XAI through natural language conversations 💬!

Fooling-LIME-SHAP. Adversarial Attacks on Post Hoc Explanation Techniques (LIME/SHAP)

Modeling-Uncertainty-Local-Explainability. Local explanations with uncertainty 💐!

Tablet. The TABLET benchmark for evaluating instruction learning with LLMs for tabular prediction.

fairness-warnings-fair-maml. Python

Finetuning-DP-Language-Models. Python

hcml-posters.

ML-Final-Project.

disentangling-vae. Experiments for understanding disentanglement in VAE latent representations