Yeah, the encoder and decoder stuff is explicit, but the internal structure in generated during training. I don't think the big labs were doing this back when I did the research; no one was back in '24.
I just didn't get round to publishing for years, because I have a day job.
By the way, it still works! I tested it earlier this year on Qen3.6 and you still see improvements, so either a) no one actually paid attention, or b) it has more room to scale.
Yeah, the encoder and decoder stuff is explicit, but the internal structure in generated during training. I don't think the big labs were doing this back when I did the research; no one was back in '24.
I just didn't get round to publishing for years, because I have a day job.
By the way, it still works! I tested it earlier this year on Qen3.6 and you still see improvements, so either a) no one actually paid attention, or b) it has more room to scale.