arxiv:2609.00455
Shubham Kumar
skumar-ml
ยท
AI & ML interests
world models & interp
Recent Activity
authored a paper 2 days ago
Measuring the (Un)Faithfulness of Concept-Based Explanations authored a paper 2 days ago
Towards a Belief-Based World Model for LLM Agents authored a paper 2 days ago
Minimal, Local, Causal Explanations for Jailbreak Success in Large Language ModelsOrganizations
