Pinned Loading

1. romovpa/claudini romovpa/claudini Public

   Autoresearch for LLM adversarial attacks

   Python 162 13

2. brendel-group/objects-compositional-generalization brendel-group/objects-compositional-generalization Public

   Official code for the paper "Provable Compositional Generalization for Object-Centric Learning" (ICLR 2024, oral)

   Jupyter Notebook 16 2

3. valentyn1boreiko/llm-threat-model valentyn1boreiko/llm-threat-model Public

   An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks [ICML 2025]

   Python 12 1

4. strategic_dishonesty_mcq strategic_dishonesty_mcq Public

   An official repository for the "Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs" paper.

   Python 4