Sihong Xie
3 papers · Latest:
Artificial Intelligence
SCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question Answering
SCPRM is a new reward model for Knowledge Graph Question Answering that uses schema-aware cumulative rewards to improve multi-hop reasoning accuracy.
2605.02819
Machine LearningA decoupled diffusion planner that adapts to changing cost limits by using cost-conditioned generation for safety and reward gradients for performance
SDGD is a decoupled diffusion planner adapting to varying safety limits via cost-conditioned generation for safety and reward gradients for performance.
2605.02777
Natural Language ProcessingGeometry-Calibrated Conformal Abstention for Language Models
A post-hoc framework, Geometry-Calibrated Conformal Abstention, enables LMs to selectively abstain from answering when uncertain, boosting correctness.
2604.27914
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.