catalyst-team/catalyst
Accelerated deep learning R&D
Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine
$ git clone https://github.com/slavabarkov/tidy.gitAccelerated deep learning R&D
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
OCR, Archive, Index and Search: Implementation agnostic OCR framework.
Easily compute clip embeddings and build a clip retrieval system with them
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and ๐ video, up to 5x faster than OpenAI CLIP and LLaVA ๐ผ๏ธ & ๐๏ธ
summaries of all the papers I read
Data from GitHub ยท snapshot Sep 24, 2026