ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models

Dhruv Parikh, Haoyang Fan, Rajgopal Kannan, Viktor K. PrasannaarXiv 2026 · DOI

BibTeX
@misc{parikh2026consensusdrop,
  author = {Dhruv Parikh and Haoyang Fan and Rajgopal Kannan and Viktor K. Prasanna},
  title = {{ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models}},
  year = {2026},
  doi = {10.48550/arxiv.2602.00946},
}

Loading related content...

Figure