Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs

Documenti analoghi

• Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
  di: Mukherjee, Sagnik, et al.
  Pubblicazione: (2025)
• Do LLMs Encode Functional Importance of Reasoning Tokens?
  di: Singh, Janvijay, et al.
  Pubblicazione: (2026)
• Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data
  di: Agarwal, Ishika, et al.
  Pubblicazione: (2025)
• SIMU: Selective Influence Machine Unlearning
  di: Agarwal, Anu, et al.
  Pubblicazione: (2025)
• ToolRL: Reward is All Tool Learning Needs
  di: Qian, Cheng, et al.
  Pubblicazione: (2025)