Yutaka Matsuo
2 papers · Latest:
Machine Learning
Does "Do Differentiable Simulators Give Better Policy Gradients?'' Give Better Policy Gradients?
This paper introduces DDCG for robust estimator switching and IVW-H for variance stabilization in policy gradients with discontinuous dynamics.
2604.18161
Machine LearningCORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation
CORA is a risk-controlled GUI agent providing statistical guarantees against harmful actions in autonomous mobile GUI automation.
2604.09155
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.