Author

Aryo Pradipta Gema

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models

This work finds that the wording of the question affects VLMs in two opposite ways: verbose paraphrasing reduces drift variance by 70--81% on the 8B models and the practical recipe---pad the prompt---further yields measurable gains in accuracy, even under image corruption.

Farooq Ahmad Wani, Maria Sofia Bucarelli, Mujtaba Hussain Mirza et al. · 0 citations

#artificial intelligence Feb 2026

Same Answer, Different Representations: Hidden instability in VLMs

A representation-aware and frequency-aware evaluation framework that measures internal embedding drift, spectral sensitivity, and structural smoothness (spatial consistency of vision tokens), alongside standard label-based metrics is introduced.

Farooq Ahmad Wani, Alessandro Suglia, Rohit Saxena et al. · arXiv.org · 2 citations