Sensitivity of Generative VLMs to Semantically and Lexically Altered Prompts

Documenti analoghi

• SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations
  di: Dumpala, Sri Harsha, et al.
  Pubblicazione: (2024)
• VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations
  di: Dumpala, Sri Harsha, et al.
  Pubblicazione: (2024)
• DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
  di: Sastry, Chandramouli, et al.
  Pubblicazione: (2023)
• Seeing Syntax: Uncovering Syntactic Learning Limitations in Vision-Language Models
  di: Dumpala, Sri Harsha, et al.
  Pubblicazione: (2024)
• Test-Time Training for Depression Detection
  di: Dumpala, Sri Harsha, et al.
  Pubblicazione: (2024)