Ostrakon-VL：面向食品服务与零售商店的领域专家MLLM
Ostrakon-VL: Towards Domain-Expert MLLM for Food-Service and Retail Stores
AI总结：
Ostrakon-VL通过多阶段训练策略在FSRS场景中取得新突破，实现60.1的高分表现，超越现有模型并展示更高参数效率。
摘要：
多模态大语言模型（MLLMs）最近在通用感知和推理方面取得了显著进展。然而，其在食品服务与零售商店（FSRS）场景中的部署却面临两大主要障碍：（i）现实中的FSRS数据，由异构采集设备收集，具有高度噪声且缺乏可审计、闭环的数据整理，这阻碍了高质量、可控和可重复训练语料的构建；（ii）现有的评估协议不提供一个统一的、细粒度和标准化的基准，涵盖单图像、多图像和视频输入，使得难以客观评估模型的鲁棒性。为了解决这些挑战，我们首先开发了Ostrakon-VL，一种基于Qwen3-VL-8B的FSRS专用MLLM。其次，我们引入了ShopBench，首个公开的FSRS基准。第三，我们提出了QUAD（质量感知无偏自动化数据整理），一种多阶段多模态指令数据整理流程。利用多阶段训练策略，Ostrakon-VL在ShopBench上取得了60.1的平均分数，建立了在参数规模相当和多样化的架构中开源MLLM的新状态。值得注意的是，它比显著更大的Qwen3-VL-235B-A22B（59.4）高出0.7，且比相同规模的Qwen3-VL-8B（55.3）高出4.8，显示出显著改进的参数效率。这些结果表明，Ostrakon-VL提供了更鲁棒和可靠的FSRS专用感知和决策能力。为了促进可重复研究，我们将公开发布Ostrakon-VL和ShopBench基准。
英文摘要：
Multimodal Large Language Models (MLLMs) have recently achieved substantial progress in general-purpose perception and reasoning. Nevertheless, their deployment in Food-Service and Retail Stores (FSRS) scenarios encounters two major obstacles: (i) real-world FSRS data, collected from heterogeneous acquisition devices, are highly noisy and lack auditable, closed-loop data curation, which impedes the construction of high-quality, controllable, and reproducible training corpora; and (ii) existing evaluation protocols do not offer a unified, fine-grained and standardized benchmark spanning single-image, multi-image, and video inputs, making it challenging to objectively gauge model robustness. To address these challenges, we first develop Ostrakon-VL, an FSRS-oriented MLLM based on Qwen3-VL-8B. Second, we introduce ShopBench, the first public benchmark for FSRS. Third, we propose QUAD (Quality-aware Unbiased Automated Data-curation), a multi-stage multimodal instruction data curation pipeline. Leveraging a multi-stage training strategy, Ostrakon-VL achieves an average score of 60.1 on ShopBench, establishing a new state of the art among open-source MLLMs with comparable parameter scales and diverse architectures. Notably, it surpasses the substantially larger Qwen3-VL-235B-A22B (59.4) by +0.7, and exceeds the same-scale Qwen3-VL-8B (55.3) by +4.8, demonstrating significantly improved parameter efficiency. These results indicate that Ostrakon-VL delivers more robust and reliable FSRS-centric perception and decision-making capabilities. To facilitate reproducible research, we will publicly release Ostrakon-VL and the ShopBench benchmark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
