Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision

Documenti analoghi

• Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from $k$-Parity
  di: Huang, Jianhao, et al.
  Pubblicazione: (2026)
• LoRA is All You Need for Safety Alignment of Reasoning LLMs
  di: Xue, Yihao, et al.
  Pubblicazione: (2025)
• Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise
  di: Xue, Yihao, et al.
  Pubblicazione: (2022)
• Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
  di: Xue, Yihao, et al.
  Pubblicazione: (2025)
• Understanding the Role of Training Data in Test-Time Scaling
  di: Javanmard, Adel, et al.
  Pubblicazione: (2025)