Gold-Switch: Training-Free Superposition of Slow- and Fast- Thinking LLMs

Documenti analoghi

• OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs
  di: Lee, Jaeseong, et al.
  Pubblicazione: (2025)
• STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning
  di: Lee, Jaeseong, et al.
  Pubblicazione: (2024)
• Fast, Slow, and Tool-augmented Thinking for LLMs: A Review
  di: Jia, Xinda, et al.
  Pubblicazione: (2025)
• Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis
  di: Lyu, Zhiheng, et al.
  Pubblicazione: (2024)
• What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
  di: Li, Ming, et al.
  Pubblicazione: (2024)