[HN Gopher] Leave No Context Behind: Efficient Infinite Context ...
       ___________________________________________________________________
        
       Leave No Context Behind: Efficient Infinite Context Transformers
        
       Author : tosh
       Score  : 11 points
       Date   : 2024-04-11 13:01 UTC (10 hours ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | Manabu-eo wrote:
       | How it compares to the many hybrid SSM/Transformer architectures
       | that are coming out now, with 2B+ weights released? I skimmed the
       | paper, but it seems it's innovation is basically combining both
       | in the same layer, instead of alternating layers, but I see no
       | reference to the latter.
        
       ___________________________________________________________________
       (page generated 2024-04-11 23:02 UTC)