Freeze and Reveal: Exposing Modality Bias in Vision-Language Models

Documenti analoghi

• One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognition
  di: Darur, Balaji, et al.
  Pubblicazione: (2026)
• AlignIT: Enhancing Prompt Alignment in Customization of Text-to-Image Models
  di: Agarwal, Aishwarya, et al.
  Pubblicazione: (2024)
• Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models
  di: Szu-Tu, Li-Zhong, et al.
  Pubblicazione: (2025)
• Communicating about Space: Language-Mediated Spatial Integration Across Partial Views
  di: Sikarwar, Ankur, et al.
  Pubblicazione: (2026)
• Test-time Conditional Text-to-Image Synthesis Using Diffusion Models
  di: Shukla, Tripti, et al.
  Pubblicazione: (2024)