Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation

Documenti analoghi

• LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generation
  di: Chen, Jizheng, et al.
  Pubblicazione: (2026)
• NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging
  di: Zhang, Weiming, et al.
  Pubblicazione: (2025)
• RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation
  di: Li, Qingyao, et al.
  Pubblicazione: (2024)
• CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation
  di: Du, Kounianhua, et al.
  Pubblicazione: (2024)
• DisCo: Towards Harmonious Disentanglement and Collaboration between Tabular and Semantic Space for Recommendation
  di: Du, Kounianhua, et al.
  Pubblicazione: (2024)