A Theoretical Lens for RL-Tuned Language Models via Energy-Based Models

Documenti analoghi

• Self-Supervised On-Policy Distillation for Reasoning Language Models
  di: Tan, Zhiquan, et al.
  Pubblicazione: (2026)
• PAINT: Partial-Solution Adaptive Interpolated Training for Self-Distilled Reasoners
  di: Tan, Zhiquan, et al.
  Pubblicazione: (2026)
• Inference-Cost-Aware Dynamic Tree Construction for Efficient Inference in Large Language Models
  di: Hong, Yinrong, et al.
  Pubblicazione: (2025)
• Information-Theoretic Perspectives on Optimizers
  di: Tan, Zhiquan, et al.
  Pubblicazione: (2025)
• Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal Balance
  di: Shen, Ao, et al.
  Pubblicazione: (2024)