@inproceedings{cao-etal-2026-mtive,
    title = "{MTIVE}: Multi-Task Image Verification Engine Using Vision-Language Models for {E}-commerce",
    author = "Cao, Yu-Tong  and
      Prabhakaran, Vishnu  and
      Das, Arunita  and
      Aggarwal, Purav  and
      Saladi, Anoop",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.143/",
    pages = "2148--2159",
    ISBN = "979-8-89176-394-4",
    abstract = "Vision-language models show promise for e-commerce automation but struggle with noisy real-world images and multi-task requirements. We introduce MTIVE, a curriculum learning framework that progressively adapts base models through three stages: continued pre-training on large-scale e-commerce datasets with contrastive learning and diverse dialogue templates, instruction tuning on synthetic data, and modular task-specific expert training. Our architecture uses frozen base weights with stacked LoRA adapters{---}shared modules for domain knowledge and lightweight task-specific experts{---}enabling continual learning without catastrophic forgetting. MTIVE outperforms open-source and proprietary baselines in both standard and continual learning settings."
}