From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training

Documenti analoghi

• KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation
  di: Guan, Ziyi, et al.
  Pubblicazione: (2025)
• Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
  di: Chen, Peter, et al.
  Pubblicazione: (2025)
• VP-Bench: A Comprehensive Benchmark for Visual Prompting in Multimodal Large Language Models
  di: Xu, Mingjie, et al.
  Pubblicazione: (2025)
• AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment
  di: Li, Kun, et al.
  Pubblicazione: (2025)
• Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning
  di: Huang, Fanding, et al.
  Pubblicazione: (2025)