Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model Adaptation

Documenti analoghi

• Mitigating Hallucination in Multimodal LLMs with Layer Contrastive Decoding
  di: Tong, Bingkui, et al.
  Pubblicazione: (2025)
• Measuring Epistemic Humility in Multimodal Large Language Models
  di: Tong, Bingkui, et al.
  Pubblicazione: (2025)
• Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning
  di: Xia, Jiaer, et al.
  Pubblicazione: (2025)
• Streaming Video Instruction Tuning
  di: Xia, Jiaer, et al.
  Pubblicazione: (2025)
• Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
  di: Wang, Yibin, et al.
  Pubblicazione: (2025)