SSRNLLMs & Text
Vision-Language Model Evaluation
The study introduces a surrogate model to assess the resilience of vision-language models to minor perturbations, using adversarial perturbations in text and image modalities.
Featured in No. 101 on 11 Jun 2025 · 6 days after release
- Released
- 5 Jun 2025
- First featured
- No. 101 · 11 Jun 2025
- Published in
- Not yet, as far as Semantic Scholar knows
- Shares when featured
- 3
- Identifier
- SSRN 5283704
Citations and venue from Semantic Scholar (ODC-BY), refreshed weekly. Summary: Quant Letter (CC BY 4.0).