Martin Trapp
2 papers · Latest:
Artificial Intelligence
Position: agentic AI orchestration should be Bayes-consistent
This paper argues for applying Bayesian principles to the orchestration layer of agentic AI systems to improve decision-making under uncertainty.
2605.00742
Natural Language ProcessingStochasticity in Tokenisation Improves Robustness
Stochastic tokenization during pre-training and fine-tuning significantly improves large language model robustness against adversarial and random perturbations.
2604.16037
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.