hyper³labs (pronounced Hypercube Labs) builds embedding models and retrieval infrastructure across text and vision. We also build open-source tools for evaluating and understanding embedding systems.
We are especially interested in how hierarchy and non-Euclidean geometry affect retrieval, and in the failures that aggregate benchmark scores hide.
- hyper3-clip-v0.5 is an open-weight vision-language embedding model for hierarchy-sensitive retrieval.
- HyperView is a workbench for exploring embedding spaces and tracing retrieval failures back to real samples.
- hyper-models provides loaders and shared interfaces for non-Euclidean embedding models.
- hyper-scatter is a WebGL scatterplot engine for large Euclidean and Poincaré embedding layouts.
- hyper-lrp contains attribution experiments for CLIP-style models.
- Are We Recognizing the Jaguar or Its Background? studies failure modes in jaguar re-identification.
- jaguar-re-id contains images and metadata used for individual jaguar identification.
