OddGridBench: Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in Multimodal Large Language Models

Documenti analoghi

• VisNumBench: Evaluating Number Sense of Multimodal Large Language Models
  di: Weng, Tengjin, et al.
  Pubblicazione: (2025)
• LlamaSeg: Image Segmentation via Autoregressive Mask Generation
  di: Deng, Jiru, et al.
  Pubblicazione: (2025)
• Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization
  di: Deng, Haolin, et al.
  Pubblicazione: (2026)
• MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding
  di: Zhu, Fengbin, et al.
  Pubblicazione: (2024)
• ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding
  di: Peng, Yi-Xing, et al.
  Pubblicazione: (2025)