Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

ITEA CLEAR: Comprehensive Learning for Enhanced AI Responsiveness

Reference number
Coordinator ALSTOM Rail Sweden AB
Funding from Vinnova SEK 14 987 334
Project duration November 2025 - November 2028
Status Ongoing
Venture Eureka cluster co-funding 

Purpose and goal

The CLEAR project aims to address the growing challenges in integrating diverse, multimodal data into industrial AI systems and improving the reliability of their outputs and decisions. By leveraging advanced AI techniques and context-aware capabilities, CLEAR will boost and capitalize on the capabilities of Large Multi-Modal Models (LMMs) and Large Language Models (LLMs) to efficiently manage complex data inputs.

Expected effects and result

CLEAR innovations are expected to reduce operational costs, increase safety, and improve system reliability across sectors such as transportation, agriculture, manufacturing, and telecommunications. At its core, CLEAR seeks to tackle the limitations of current AI systems for industrial applications in processing a wide range of real-time, multi-modal data —including satellite and on-ground visual data, emergency response, geospatial, and time-series data.

Planned approach and implementation

To achieve the project´s goals, a strong international consortium of industry and research partners with complementary expertise has been formed. The project work is structured in six work packages: establishment of industrial use cases and demonstrators (WP1), data aggregation and fusion (WP2), model construction, fine-tuning and benchmarking (WP3), CLEAR multimodal pipelines (WP4), dissemination and exploitation (WP5) and project management (WP6). WP3 and WP6 are led by the Swedish consortium.

External links

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 27 October 2025

Reference number 2025-01170