Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers

DeepTrendLab's Take on Training and Finetuning Multimodal Embedding & Reranker...

Sentence Transformers now enables training multimodal embedding and reranker models on custom data. A finetuned Qwen3-VL model for Visual Document Retrieval achieved 0.947 NDCG@10, outperforming larger existing models.