Yi Tay
speaker
925 appearances
1 recordings
1 series
first heard Jan 2026
last heard 23 Jan
Yi Tay’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 1 in all, peaking in Jan 2026 with 1.
Appearances
So I think generative retrieval and generative rexis is very conflated.
DSI started as a retrieval thing.
So we did like natural questions, like ranking of like doc documents and everything.
It started off as I mean that's actually we did an interview with Yannick, like me and Don we did an interview with when the paper came out like a long time ago.
So at that time we wanted to like reimagine retrieval and such.
So we wanted at that time, LM really.
We were still using T5 models at the time.
It was like not we were not in the LM era yet, it was pre-LM era.
It was like, okay, pre-training works kind of thing.
And then there were like some pre-trained models around.
So we wanted to re reimagine retrieval, right?
But retrieval rexis, they're all the same formulation, ranking, retrieval problem, right?
And then that's where we started to imagine retrieval as one giant that that encodes everything in the memory.
The we tried so many different like semantic ideas, actually, my collaborator Vin was the one that came up with ideas, semantic ideas uh ideas that basically and the start of this whole genetic retrieval was actually basically
Literally just trying to give a document like identifier and that's predicting like raw brute force predicting like this.
It actually like it actually works because the models can memorize some something.
If you look at the literature from all the way to things like Doc to Vec or this very off like
Model the words have no meaning, they're just ID in in the vocabulary.
It's another number, right?
And technically the models have enough capacity to pr p predict.
Showing 661–680 of 925 · page 34 of 47
← Previous
Next →