Update README.md

README.md

@@ -15,6 +15,8 @@ The encoder-model was trained for the e-commerce search query similarity task, a
 
 The dataset for validation, which was manually annotated, comprised 362,000 instances.
 
+[Fedor Krasnov, Fedor Kurushin, and Egor Mogilevich "Custom shared encoder for enhanced recall in e-commerce product search task", Proc. SPIE 13730, Second International Conference on Computing, Machine Learning, and Data Science (CMLDS 2025), 137300B (21 July 2025);](https://doi.org/10.1117/12.3072295)
+
 ![Validation results](https://huggingface.co/fkrasnov2/SBE/resolve/main/bvf_recall1k_query_len_eng.svg)