JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization.
ArtEdit-Bench. We construct ArtEdit-Bench, comprising two subsets: (1) ArtEdit-Bench-Lr (800 samples: 400 English, 400 Chinese), selected from the ArtEdit-Lr dataset. It evaluates both global and local fine-grained retouching capabilities. (2) ArtEdit-Bench-Eval (200 English samples), sampled from ArtEdit-Eval, is used to fairly assess the model’s self-evaluation… See the full description on the dataset page:
https://huggingface.co/datasets/JarvisEvo/ArtEdit-Bench.
