SkyJM-Gen-9B is now live on ModelScope! A 9B visual reward model for text-to-image generation that ranks candidate images with prompt-conditioned rubrics, not a single flat score.๐
๐ค
๐ Text-to-image judging: tops listed reward models on MMRB2, GenAI-Bench, and GenAI-Bench-Verified, with 72.0 / 74.1 / 84.5
๐งฉ RubricRM workflow: generates evaluation dimensions, weights, and scoring descriptors for each prompt, then scores both candidate images by dimension
โ๏ธ Training recipe: rubric-trajectory SFT + dimension-level GRPO for more structured preference judgment
Apache 2.0. vLLM and Transformers ready.