See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment

Documenti analoghi

• Robust Atypical Mitosis Classification with DenseNet121: Stain-Aware Augmentation and Hybrid Loss for Domain Generalization
  di: Dukre, Adinath, et al.
  Pubblicazione: (2025)
• MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images
  di: Deria, Ankan, et al.
  Pubblicazione: (2026)
• Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning
  di: Deria, Ankan, et al.
  Pubblicazione: (2025)
• VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
  di: Kolli, Govinda, et al.
  Pubblicazione: (2026)
• TuLaBM: Tumor-Biased Latent Bridge Matching for Contrast-Enhanced MRI Synthesis
  di: Rege, Atharva, et al.
  Pubblicazione: (2026)