Pith. sign in

Finally, the QA pairs are deduplicated using both exact match and Llama-3.1-8B

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Can VLMs Recall Factual Associations From Visual References?

cs.CV · 2025-08-22 · conditional · novelty 6.0

Vision-language models recall facts much better when the entity is named in text than when the same entity appears only in an image, and hidden-state probes can detect many of these recall failures.

citing papers explorer

Showing 1 of 1 citing paper.

  • Can VLMs Recall Factual Associations From Visual References? cs.CV · 2025-08-22 · conditional · none · ref 5

    Vision-language models recall facts much better when the entity is named in text than when the same entity appears only in an image, and hidden-state probes can detect many of these recall failures.