MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models

Documenti analoghi

• Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models
  di: Lei, Xuanyu, et al.
  Pubblicazione: (2024)
• Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
  di: Fang, Hao, et al.
  Pubblicazione: (2025)
• Do Vision-Language Models Really Understand Visual Language?
  di: Hou, Yifan, et al.
  Pubblicazione: (2024)
• MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models
  di: Xia, Yinan, et al.
  Pubblicazione: (2025)
• M-MRE: Extending the Mutual Reinforcement Effect to Multimodal Information Extraction
  di: Gan, Chengguang, et al.
  Pubblicazione: (2025)