{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:05:39Z","timestamp":1772222739247,"version":"3.50.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032050595","type":"print"},{"value":"9783032050601","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-05060-1_20","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T07:58:54Z","timestamp":1758009534000},"page":"231-242","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Tracing Information Flow in\u00a0LLaMA Vision: A Step Toward Multimodal Understanding"],"prefix":"10.1007","author":[{"given":"Alessia","family":"Saporita","sequence":"first","affiliation":[]},{"given":"Vittorio","family":"Pipoli","sequence":"additional","affiliation":[]},{"given":"Federico","family":"Bolelli","sequence":"additional","affiliation":[]},{"given":"Lorenzo","family":"Baraldi","sequence":"additional","affiliation":[]},{"given":"Andrea","family":"Acquaviva","sequence":"additional","affiliation":[]},{"given":"Elisa","family":"Ficarra","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"20_CR1","unstructured":"Alayrac, J.B., et\u00a0al.: Flamingo: a Visual Language Model for Few-Shot Learning. In: Advances in Neural Information Processing Systems (2022)"},{"key":"20_CR2","unstructured":"Almazrouei, E., et\u00a0al.: The falcon series of open language models (2023). arXiv preprint arXiv:2311.16867"},{"key":"20_CR3","unstructured":"Anthropic: The Claude 3 Model Family: Opus, Sonnet, Haiku. In: OpenAI (2024)"},{"key":"20_CR4","unstructured":"Awadalla, A., et\u00a0al.: OpenFlamingo: An open-source framework for training large autoregressive vision-language models (2023). arXiv preprint arXiv:2308.01390"},{"key":"20_CR5","unstructured":"Basu, S., et\u00a0al.: Understanding information storage and transfer in multi-modal large language models (2024). arXiv preprint arXiv:2406.04236"},{"key":"20_CR6","unstructured":"Chowdhery, A., et\u00a0al.: PaLM: Scaling Language Modeling with Pathways. J. Mach. Learn. Res. 24(240) (2023)"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Clark, K., et\u00a0al.: What Does BERT Look At? An Analysis of BERT\u2019s Attention (2019). arXiv preprint arXiv:1906.04341","DOI":"10.18653\/v1\/W19-4828"},{"key":"20_CR8","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale (2020). arXiv preprint arXiv:2010.11929"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Fang, Y., et\u00a0al.: EVA: Exploring the limits of masked visual representation learning at scale. In: Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Goyal, Y., et\u00a0al.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"20_CR11","unstructured":"Grattafiori, A., et\u00a0al.: The Llama 3 Herd of Models (2024). arXiv preprint arXiv:2407.21783"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Han, J., et\u00a0al.: OneLLM: One framework to align all modalities with language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"20_CR13","unstructured":"Hui, B., et\u00a0al.: Qwen2. 5 - Coder Technical Report (2024). arXiv preprint arXiv:2409.12186"},{"key":"20_CR14","unstructured":"Li, J., et\u00a0al.: BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning (2023)"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et\u00a0al.: Microsoft COCO: Common Objects in Context. In: European Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"20_CR16","unstructured":"Liu, H., et\u00a0al.: Visual instruction tuning (2023)"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Mathew, M., et\u00a0al.: DocVQA: A dataset for VQA on document images. In: Winter Conference on Applications of Computer Vision (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"20_CR18","unstructured":"Meng, K., et\u00a0al.: Locating and editing factual associations in GPT. In: Advances in Neural Information Processing Systems (2022)"},{"key":"20_CR19","unstructured":"Meng, K., et\u00a0al.: Mass-Editing Memory in a Transformer (2022). arXiv preprint arXiv:2210.07229"},{"key":"20_CR20","unstructured":"Neo, C., et\u00a0al.: Towards interpreting visual information processing in vision-language models (2024). arXiv preprint arXiv:2410.07149"},{"key":"20_CR21","unstructured":"OpenAI: GPT-4o mini: advancing cost-efficient intelligence (2024). https:\/\/openai.com\/index\/gpt-4o-mini-advancing-cost-efficient-intelligence\/"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Palit, V., et\u00a0al.: Towards vision-language mechanistic interpretability: a causal tracing tool for BLIP. In: International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCVW60793.2023.00307"},{"key":"20_CR23","unstructured":"Park, K., et\u00a0al.: The linear representation hypothesis and the geometry of large language models (2023). arXiv preprint arXiv:2311.03658"},{"key":"20_CR24","unstructured":"Pipoli, V., et\u00a0al.: MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models. In: International Conference on Computer Vision (2025)"},{"key":"20_CR25","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"20_CR26","unstructured":"Team, G., et\u00a0al.: Gemma: open models based on gemini research and technology (2024). arXiv preprint arXiv:2403.08295"},{"key":"20_CR27","unstructured":"Touvron, H., et\u00a0al.: LLaMA: Open and efficient foundation language models (2023). arXiv preprint arXiv:2302.13971"},{"key":"20_CR28","unstructured":"Vaswani, A., et\u00a0al.: Attention Is All You Need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Yin, H., et\u00a0al.: Lifting the veil on visual information flow in MLLMs: unlocking pathways to faster inference. In: Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.00876"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, L., et\u00a0al.: Mechanistic unveiling of transformer circuits: self-influence as a key to model reasoning (2025). arXiv preprint arXiv:2502.09022","DOI":"10.18653\/v1\/2025.findings-naacl.76"},{"key":"20_CR31","unstructured":"Zhang, X., et\u00a0al.: From redundancy to relevance: information flow in LVLMs across reasoning tasks (2024). arXiv preprint arXiv:2406.06579"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et\u00a0al.: Cross-modal information flow in multimodal large language models (2024). arXiv preprint arXiv:2411.18620","DOI":"10.1109\/CVPR52734.2025.01842"},{"key":"20_CR33","unstructured":"Zhu, D., et\u00a0al.: MiniGPT-4: Enhancing vision-language understanding with advanced large language models (2023). arXiv preprint arXiv:2304.10592"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et\u00a0al.: Visual7w: Grounded question answering in images. In: Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.540"}],"container-title":["Lecture Notes in Computer Science","Computer Analysis of Images and Patterns"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05060-1_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T07:59:14Z","timestamp":1758009554000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05060-1_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"ISBN":["9783032050595","9783032050601"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05060-1_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"17 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no conflicts of interest to declare.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"CAIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Analysis of Images and Patterns","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Las Palmas de Gran Canaria","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/caip2025.com","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}