SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

Documenti analoghi

• DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning
  di: Wan, Zhongwei, et al.
  Pubblicazione: (2026)
• Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS
  di: Dou, Alex ZH, et al.
  Pubblicazione: (2025)
• MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation
  di: Wan, Zhongwei, et al.
  Pubblicazione: (2024)
• CoRe-Code: Collaborative Reinforcement Learning for Code Generation
  di: Dou, Zhihao, et al.
  Pubblicazione: (2026)
• MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference
  di: Wan, Zhongwei, et al.
  Pubblicazione: (2025)