You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models

Documenti analoghi

• VLSlice: Interactive Vision-and-Language Slice Discovery
  di: Slyman, Eric, et al.
  Pubblicazione: (2023)
• Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks
  di: Yang, Zijiao, et al.
  Pubblicazione: (2024)
• Statistical Challenges with Dataset Construction: Why You Will Never Have Enough Images
  di: Goldman, Josh, et al.
  Pubblicazione: (2024)
• No One Knows the State of the Art in Geospatial Foundation Models
  di: Corley, Isaac, et al.
  Pubblicazione: (2026)
• Know What You do Not Know: Verbalized Uncertainty Estimation Robustness on Corrupted Images in Vision-Language Models
  di: Borszukovszki, Mirko, et al.
  Pubblicazione: (2025)