Ostrakon-VL: Towards Domain-Expert MLLM for Food-Service and Retail Stores

TL;DR

Ostrakon-VL is a domain-specific multimodal language model tailored for food-service and retail environments, featuring a new benchmark and data curation pipeline to improve robustness and efficiency.

Contribution

The paper introduces Ostrakon-VL, a specialized MLLM for FSRS, along with ShopBench benchmark and QUAD data curation pipeline, advancing robustness and parameter efficiency.

Findings

Achieved state-of-the-art 60.1 score on ShopBench

Outperformed larger models like Qwen3-VL-235B by +0.7 points

Demonstrated improved parameter efficiency and robustness

Abstract

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.