HubNSW/FlatNav benchmark--new HNSW-like NNS library

[jianshu93]

Dear Ann-benchmark team,

I am wondering whether the recently developed FlatNav (https://github.com/BlaiseMuhirwa/flatnav, paper here: https://arxiv.org/abs/2412.01940) or simple HubNSW, which use hubs in the dataset instead of hierarchy to guide navigation. According to my test, it is more accurate without losing speed and can be equally applied to datasets with more than 32 dimensions. They have python bindings so I think it is very easy to add to Ann-benchmark.

Let me know your thoughts for this.

Best,
Jianshu