SkyJM-Gen-4B

SkyJM（RubricRM） is a reward model for visual generation, covering both text-to-image generation and image editing. Given a prompt and two candidate images, it predicts which one better satisfies the instruction. RubricRM performs the following in a single forward pass:

• Dynamically produces an evaluation rubric conditioned on the prompt — including evaluation dimensions, per-dimension weights, and graded scoring descriptors;
• Scores both candidate images at the dimension level under that rubric;
• Aggregates the dimension scores via the rubric weights to derive the final preference.

We release two model sizes built on the Qwen3.5 backbone:

• SkyJM-Gen-4B / SkyJM-Gen-9B — for text-to-image generation
• SkyJM-Edit-4B / SkyJM-Edit-9B — for image editing

Performance

Text-to-image generation

Image editing

Training Strategy

Stage 1: Rubric-trajectory SFT. We use Gemini 3.1 Pro to synthesize rubric-based evaluation trajectories conditioned on human preference labels, then filter them with structural and label-consistency checks for SFT.

Stage 2: Dimension-level GRPO. During RL, we fix the rubric and optimize only the scoring process using rewards based on per-dimension score gaps, with saturated-group filtering to suppress noisy low-variance updates.

Quick Start

For detailed usage instructions, installation guide, and inference examples (supporting both vLLM and Transformers backends), please refer to the official inference framework:

SKYLENAGE-JUDGER — Unified inference framework for SkyJM judge models.

Link

• GitHub: SKYLENAGE-AI/SKYLENAGE-JUDGER
• Hugging Face Models:
  • skylenage-ai/SkyJM-Gen-4B
  • skylenage-ai/SkyJM-Gen-9B
  • skylenage-ai/SkyJM-Edit-4B
  • skylenage-ai/SkyJM-Edit-9B
• Hugging Face Dataset: skylenage-ai/RubricRM-Data
• ModelScope Models:
  • SKYLENAGE/SkyJM-Gen-4B
  • SKYLENAGE/SkyJM-Gen-9B
  • SKYLENAGE/SkyJM-Edit-4B
  • SKYLENAGE/SkyJM-Edit-9B

Citation

If you find this model useful, please cite our paper:

@misc{kan2026rubricrmgenerativerewardmodeling,
      title={RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and Editing}, 
      author={Zijian Kan and Wei Wang and Long Luo and Bing Zhao and Xuan Ren and Weixu Qiao and Wenbo Li and Hu Wei and Lin Qu},
      year={2026},
      eprint={2608.26956},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2608.26956}, 
}