vov_or
- Karma
- 285
- Created
- March 23, 2022 (4y ago)
- Submissions
- 0
Senior NLP research engineer
-
I want to share the most recent model release we have prepared. It's a Vision-Language understanding Transformer. It has 40% fewer parameters than vanilla CLIP while performing much better on text-to-image retrieval,…
- From Dating to Vector Search – “Stable Marriages” on a Global Scale (ashvardanian.com)
- Abusing vector search for texts, maps, and chess (ashvardanian.com)
- Beating OpenAI CLIP with 100x less data and compute (unum.cloud)