Skeleton-Guided Direct Preference Optimization
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
SkelDPO: A Skeleton-Guided Direct Preference Optimization Framework for Efficient Code Generation
arXiv:2606.06826v1 Announce Type: new Abstract: With the remarkable progress of Code Large Language Models (Code LLMs) in achieving semantic correctness, execution efficiency has become an increasingly important dimension for evaluating their practical utility. However, existing approaches typically treat full programs as a single optimization target during training, without explicitly modeling the structural factors that influence efficiency. As a result, although these models can generate...