Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models

Documenti analoghi

• Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
  di: Ma, Ji, et al.
  Pubblicazione: (2026)
• Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
  di: Peng, Ruiying, et al.
  Pubblicazione: (2026)
• Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning
  di: Zhang, Chi, et al.
  Pubblicazione: (2025)
• Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofing
  di: Zhang, Honglu, et al.
  Pubblicazione: (2025)
• Watch Wider and Think Deeper: Collaborative Cross-modal Chain-of-Thought for Complex Visual Reasoning
  di: Lu, Wenting, et al.
  Pubblicazione: (2026)