Beyond the Vision Encoder: Identifying and Mitigating Spatial Bias in Large Vision-Language Models

Documenti analoghi

• Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning
  di: Zhu, Yingjie, et al.
  Pubblicazione: (2024)
• Evaluating and Steering Modality Preferences in Multimodal Large Language Model
  di: Zhang, Yu, et al.
  Pubblicazione: (2025)
• Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
  di: Zhang, Hongbin, et al.
  Pubblicazione: (2026)
• Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model
  di: Zhang, Hongbin, et al.
  Pubblicazione: (2024)
• Mitigating Multimodal Hallucination via Phase-wise Self-reward
  di: Zhang, Yu, et al.
  Pubblicazione: (2026)