Introduces QCalEval benchmark showing best zero-shot VLM score of 72.3 on quantum calibration plots, with fine-tuning and in-context learning effects varying by model type.
Scifibench: Benchmarking large multimodal models for scientific figure interpretation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
quant-ph 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding
Introduces QCalEval benchmark showing best zero-shot VLM score of 72.3 on quantum calibration plots, with fine-tuning and in-context learning effects varying by model type.