Introduces FEPBench benchmark to evaluate T2I models on instruction faithfulness, reasoning enrichment, and semantic precision for natural-science illustrations using atom set annotations.
Ovis-image technical report
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
The NTIRE 2026 challenge provides a dataset of over 294,000 real and AI-generated images with 36 transformations to benchmark robust detection models.
citing papers explorer
-
Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models
Introduces FEPBench benchmark to evaluate T2I models on instruction faithfulness, reasoning enrichment, and semantic precision for natural-science illustrations using atom set annotations.
-
NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild
The NTIRE 2026 challenge provides a dataset of over 294,000 real and AI-generated images with 36 transformations to benchmark robust detection models.