MMMG introduces 49 evaluation tasks (29 new) and 937 instructions across four modality combinations, reporting 94.3% average agreement between its automated evaluators and human judgments.
When crafting image prompts, follow these guidelines: For image prompts: • Provide detailed, specific descriptions (15-30 words) for optimal results
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MMMG: a Comprehensive and Reliable Evaluation Suite for Multitask Multimodal Generation
MMMG introduces 49 evaluation tasks (29 new) and 937 instructions across four modality combinations, reporting 94.3% average agreement between its automated evaluators and human judgments.