Views
No views yet
Qwen/Qwen-Image-Bench (Q-Judger) — a vision-language judge model fine-tuned by the Qwen team for automated evaluation of text-to-image generation quality.llm-compressor (vLLM project) — see recipe.yaml in the repo for the exact QuantizationModifier config.1default_stage:
2 default_modifiers:
3 QuantizationModifier:
4 targets: [Linear]
5 ignore: ['re:.*lm_head', 're:visual.*', 're:model.visual.*', 're:.*embed_tokens$']
6 scheme: NVFP4
7 bypass_divisibility_checks: falserecipe.yaml is included for reproducibility.(dense + vision) weight loader path in Atlas's qwen35_dense.rs factory branch. See [TODO: link to filed issue] for details.Qwen/Qwen-Image-Bench.1@misc{li2026qwenimagebenchgenerationcreationtexttoimage,
2 title={Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation},
3 author={Niantong Li and Guangzheng Hu and Weixu Qiao and Ying Ba and Qichen Hong and Shijun Shen and Jinlin Wang and Fan Zhou and Jianye Kang and Xin Shang and Ziyi He and Wei Wang and Dalin Li and Jiahao Li and Jie Zhang and Kaiyuan Gao and Kun Yan and Lihan Jiang and Ningyuan Tang and Shengming Yin and Tianhe Wu and Xiao Xu and Xiaoyue Chen and Yuxiang Chen and Yan Shu and Yanran Zhang and Yilei Chen and Yixian Xu and Zekai Zhang and Zhendong Wang and Zihao Liu and Zikai Zhou and Hongzhu Shi and Yi Wang and Bing Zhao and Hu Wei and Lin Qu and Chenfei Wu},
4 year={2026},
5 eprint={2605.28091},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV},
8 url={https://arxiv.org/abs/2605.28091},
9}