BIGBALLON/BeyondCLIP

Not a neutral survey — a field manual for engineers who build, train, and ship multimodal retrieval at production scale. The C-L-I triangle (Compression · Localization · Instruction), MLLM encoders vs late interaction, MUVERA economics, and falsifiable forecasts through 2030.

语言：HTML · GitHub 星标：83 · Fork：5

话题：composed-image-retrieval · image-retrieval · image-search · information-retrieval · large-language-models · multimodel-large-language-model · retrieval · text-image-retrieval

在 GitHub 上查看原仓库