When and Why Does Unsupervised RL Succeed in Mathematical Reasoning? A Manifold Envelopment Perspective

Documenti analoghi

• Predicting Where Steering Vectors Succeed
  di: Billa, Jayadev
  Pubblicazione: (2026)
• Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
  di: Kim, Jeonghye, et al.
  Pubblicazione: (2026)
• Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
  di: Puerto, Haritz, et al.
  Pubblicazione: (2024)
• RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?
  di: Sun, Yiyou, et al.
  Pubblicazione: (2025)
• Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)
  di: Bi, Jing, et al.
  Pubblicazione: (2025)