Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
AdamX: Cosine similarity meets gradient descent
Francisco Caldas, Ruben Belo, Cláudia Soares
We introduce AdamX, a first-order optimizer that incorporates cosine similarity as an adaptive mechanism for controlling update magnitudes. The proposed method is scalable, model-a…
cs.LG2026
CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks
Francisco Caldas, Sahil Satish Kumar, Ruben Belo +1
Explainable Artificial Intelligence aims to make black-box models more trustworthy by presenting, in a human-understandable manner, the elements that lead to the model's output. Th…
cs.LG2025
Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers
Ruben Belo, Marta Guimaraes, Claudia Soares
Large Language Models are susceptible to jailbreak attacks that bypass built-in safety guardrails (e.g., by tricking the model with adversarial prompts). We propose Concept Alignme…