SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning

Documenti analoghi

• Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
  di: Xiang, Bajian, et al.
  Pubblicazione: (2025)
• Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data
  di: Zhao, Shuaijiang, et al.
  Pubblicazione: (2024)
• Technical Report: Competition Solution For BetterMixture
  di: Zhao, Shuaijiang, et al.
  Pubblicazione: (2024)
• How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study
  di: Ji, Yunjie, et al.
  Pubblicazione: (2025)
• TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning
  di: Wu, Jinyang, et al.
  Pubblicazione: (2025)