Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Documenti analoghi

• Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
  di: Zou, Xin, et al.
  Pubblicazione: (2024)
• When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition
  di: Sun, Xiaokun, et al.
  Pubblicazione: (2026)
• Critique Before Thinking: Mitigating Hallucination through Rationale-Augmented Instruction Tuning
  di: Yang, Zexian, et al.
  Pubblicazione: (2025)
• Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation
  di: Zhu, Xingyu, et al.
  Pubblicazione: (2026)
• Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models
  di: Jian, Pu, et al.
  Pubblicazione: (2025)