The 2nd EReL@MIR Workshop on Efficient Representation Learning for Multimodal Information Retrieval
For researchers in multimodal information retrieval, this workshop addresses practical deployment issues of large models, though it is a proposal rather than a technical contribution.
The paper proposes organizing a workshop to address efficiency bottlenecks in adapting large multimodal foundation models for information retrieval tasks, aiming to foster discussion on solutions, challenges, and new metrics.
Multimodal representation learning has attracted increasing attention in AI, driven by the strong performance of large, pretrained multimodal foundation models such as Qwen, LLaVA, and CLIP. These models deliver impressive performance on a range of multimodal information retrieval (MIR) tasks, including web search, cross-modal retrieval, and recommender systems. Yet their massive parameter counts create major efficiency bottlenecks when adapting their representations for IR tasks during training, deployment, and inference. These limitations hinder the practical use of foundation models for representation learning in information retrieval. To address these issues, we propose organizing the EReL@MIR workshop at MM 2026, bringing together researchers from academia and industry to discuss emerging solutions, open challenges, and new efficiency metrics and benchmarks for multimodal IR representation learning in the foundation-model era. The workshop's official website is available at https://erel-mir.github.io/.