From Captioning to Multimodal Reasoning: The Evolution of Vision-Language Research in the Era of Multimodal LLMs.

@inproceedings{cornia-2026-captioning, author = {Marcella Cornia}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{From Captioning to Multimodal Reasoning: The Evolution of Vision-Language Research in the Era of Multimodal LLMs}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {1}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3819063}, doi = {https://doi.org/10.1145/3805622.3819063} }