I wonder, is this exponential relation specific to multi-modal models? From my admittedly naïve view it seems to make sense that "...what is rare is not properly learned" would apply generally?
Undoubtedly that can be the cause in some cases, but there are counterexamples. Like West Virginia which has a bad opioid addiction problem yet relatively low homeless rate. What does appear highly correlated is…
Agree in that “Startups” imply scale and that’s just race to the bottom clickbait with maybe a little real news on the side. However, one example here in Canada is “Canadaland”, which is profitable, funded partly by…
I wonder, is this exponential relation specific to multi-modal models? From my admittedly naïve view it seems to make sense that "...what is rare is not properly learned" would apply generally?
Undoubtedly that can be the cause in some cases, but there are counterexamples. Like West Virginia which has a bad opioid addiction problem yet relatively low homeless rate. What does appear highly correlated is…
Agree in that “Startups” imply scale and that’s just race to the bottom clickbait with maybe a little real news on the side. However, one example here in Canada is “Canadaland”, which is profitable, funded partly by…