Michael Hahn
2 papers · Latest:
Natural Language Processing
SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts
SafeReview defends LLM-based peer review systems against adversarial hidden prompts using a co-evolving generator-defender framework.
2604.26506
Machine LearningBarriers to Universal Reasoning With Transformers (And How to Overcome Them)
Transformers with Chain-of-Thought struggle with length generalization beyond TC^0, but a new signpost token method enables Turing-complete reasoning.
2604.25800
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.