PLPP: Prompt Learning with Perplexity Is Self-Distillation for Vision-Language Models

Documenti analoghi

• When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models
  di: Kostelec, Juan Gabriel, et al.
  Pubblicazione: (2026)
• Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models
  di: Liu, Biao, et al.
  Pubblicazione: (2025)
• On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation
  di: Hsu, Chan-Jan, et al.
  Pubblicazione: (2026)
• SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data
  di: Fang, Wenkai, et al.
  Pubblicazione: (2025)
• I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses
  di: Ren, Xuan, et al.
  Pubblicazione: (2024)