Verification of the Implicit World Model in a Generative Model via Adversarial Sequences
Paper
• 2602.05903 • Published
András Balogh
Erasiel
AI & ML interests
Interpretability, security and robustness in deep learning
Recent Activity
authored
a paper
2 days ago
Verification of the Implicit World Model in a Generative Model via Adversarial Sequences authored
a paper
2 days ago
How not to Stitch Representations to Measure Similarity: Task Loss Matching versus Direct Matching updated
a dataset 3 days ago
Erasiel/chess-datasets Organizations
None yet