Cited by: On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

4 citation edges inside this catalog. A title match is weaker evidence than an identifier match. Zero entries does not mean no citations on the web.

• On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
  arxiv:2508.11408 · evidence: id
• Self-Distillation Enables Continual Learning
  arxiv:2601.19897 · evidence: id
• Weight-Space Geometry of Offline Reasoning Training
  arxiv:2606.23740 · evidence: id
• Finetuning with Sampling: SFT Learns Better Than You Think
  arxiv:2610.02140 · evidence: id