SOURCE-LINKED INTELLIGENCE

Learning a Universal Similarity Function

CORDIS · observation · Publication date unknown

Secondly, it streamlines the integration of synthetic data during training, a key ingredient for large-scale training of a foundational model. The model architecture is grounded in transformer-based deep learning modules and will be fortified by pioneering positional encodings rooted in kernel methods. These positional encodings empower us to effectively manage the differing part topologies encountered across diverse domains -- a formidable challenge in itself. The work program commences by focusing on a single domain and task but is thoughtfully designed for extensibility. The ultimate goal is creating a foundational model capable of accommodating all modalities -- visual, audio, text -- and supporting a broad range of similarity types, including uni-modal, cross-modal, and multi-modal scenarios. LUSt's commitment to universality will be thoroughly validated through comprehensive benchmarking, spanning numerous tasks and domains. similarity learning, multimodal learning, foundational model, positional encoding, self-supervised learning, deep learning, computer vision

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

150438.72

unit

EUR