AImageLab publications export - 14 publications; author=dcaffagni

Mambelli, A., Bigoni, L., Dainese, D., Tutrone, F., Caffagni, D., Cocchi, F., Zanella, M., Cornia, M., & Cucchiara, R. (2026). The Biblical Heritage in Ancient Latin Christian Literature: Advancing Intertextual Mapping Through Sentence Embeddings. UMANISTICA DIGITALE. https://doi.org/10.60923/issn.2532-8816/22160

Compagnoni, A., Morini, M., Sarto, S., Cocchi, F., Caffagni, D., Cornia, M., Baraldi, L., & Cucchiara, R. (2026). ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering. IEEE/CVF Conference on Computer Vision and Pattern Recognition Denver (CO). https://iris.unimore.it/handle/11380/1396973

Caffagni, D., Compagnoni, A., Melis, F., Sarto, S., Luigi Dovesi, P., Granroth-Wilding, M., Cornia, M., & Baraldi, L. (2026). Mind the Heads: Topological Representation Alignment for Multimodal LLMs. Conference on Neural Information Processing Systems (NeurIPS). https://iris.unimore.it/handle/11380/1418988

Caffagni, D., Cocchi, F., Mambelli, A., Tutrone, F., Zanella, M., Cornia, M., & Cucchiara, R. (2026). Generating Synthetic Data with Large Language Models for Low-Resource Sentence Retrieval. International Conference on Theory and Practice of Digital Libraries (TPDL). https://doi.org/10.1007/978-3-032-05409-8_4

Caffagni, D., Sarto, S., Cornia, M., Baraldi, L., & Cucchiara, R. (2026). Recurrence Meets Transformers for Universal Multimodal Retrieval. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. https://doi.org/10.1109/tpami.2026.3729293

Cocchi, F., Moratelli, N., Caffagni, D., Sarto, S., Baraldi, L., Cornia, M., & Cucchiara, R. (2025). LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning. IEEE/CVF International Conference on Computer Vision Workshops Honolulu, Hawaii. https://iris.unimore.it/handle/11380/1387168

Caffagni, D., Sarto, S., Cornia, M., Baraldi, L., & Cucchiara, R. (2025). Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR52734.2025.00867

Caffagni, D., Cornia, M., Baraldi, L., & Cucchiara, R. (2025). Augmenting and Mixing Transformers with Synthetic Data for Image Captioning. IMAGE AND VISION COMPUTING. https://doi.org/10.1016/j.imavis.2025.105661

Caffagni, D., Cocchi, F., Mambelli, A., Tutrone, F., Zanella, M., Cornia, M., & Cucchiara, R. (2025). Benchmarking BERT-based Models for Latin: A Case Study on Biblical References in Ancient Christian Literature. Conference on Information and Research Science Connecting to Digital and Library Science (IRCDL). https://iris.unimore.it/handle/11380/1371269

Compagnoni, A., Caffagni, D., Moratelli, N., Baraldi, L., Cornia, M., & Cucchiara, R. (2025). Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization. British Machine Vision Conference Sheffield, UK 24th - 27th. https://iris.unimore.it/handle/11380/1383748

Caffagni, D., Cocchi, F., Moratelli, N., Sarto, S., Cornia, M., Baraldi, L., & Cucchiara, R. (2024). Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). https://doi.org/10.1109/CVPRW63382.2024.00188

Caffagni, D., Cocchi, F., Barsellotti, L., Moratelli, N., Sarto, S., Baraldi, L., Baraldi, L., Cornia, M., & Cucchiara, R. (2024). The Revolution of Multimodal Large Language Models: A Survey. Annual Meeting of the Association-for-Computational-Linguistics (ACL). https://iris.unimore.it/handle/11380/1338749

Moratelli, N., Caffagni, D., Cornia, M., Baraldi, L., & Cucchiara, R. (2024). Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization. British Machine Vision Conference (BMVC). https://iris.unimore.it/handle/11380/1347746

Caffagni, D., Barraco, M., Cornia, M., Baraldi, L., & Cucchiara, R. (2023). SynthCap: Augmenting Transformers with Synthetic Data for Image Captioning. International Conference on Image Analysis and Processing (ICIAP). https://doi.org/10.1007/978-3-031-43148-7_10