ImageBind: One Embedding Space To Bind Them All · HackerPapers discussions

ImageBind: One Embedding Space To Bind Them All — mentioned by fzliu

Fri, 10 May 2024 08:12:53 GMT

> I think a few details (and perhaps a small amount of customization) would go a long way. I hear you and agree 100% - I unfortunately haven't gotten around to writing better documentation nor solid code samples that utilize Radient yet. Regarding molecule vectorization: that capability comes from RDKit (https://rdkit.org) - I just uploaded a sample to the /examples directory. You're right that molecule-to-audio and audio-to-molecule search is nonsensical from a semantic perspective, but I could see a third modality such as text or images that ties the two together, similar to what ImageBind…

Paper and discussion history. A mention is not an endorsement.

ImageBind: One Embedding Space To Bind Them All — mentioned by AndrewKemendo

Sat, 03 Jun 2023 19:47:28 GMT

I definitely appreciate the technical privacy focus here and I’m curious if that is the whole purpose here. I don’t see that many benefits to this method other than privacy - the ability to process multiple data types with a singular architecture is really cool but not SOTA beating or comparable really to large multimodal systems like imagebind [1] [1] https://arxiv.org/pdf/2305.05665.pdf

Paper and discussion history. A mention is not an endorsement.

ImageBind: One Embedding Space To Bind Them All — HN submission

Thu, 11 May 2023 03:02:03 GMT

ImageBind: One Embedding Space to Bind Them All

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.