[R] Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions
https://arxiv.org/pdf/2410.06577
Discussions: https://discu.eu/q/https://arxiv.org/pdf/2410.06577
#compsci #machinelearning
Compsci Weekly /
npub12y…mwm90
2024-10-13 07:24:55
Author Public Key
npub12yxz5pw6kxawd4wshrvzkrdzyp772te52nzdeujcdjsjxngcqulsqmwm90Published at
2024-10-13 07:24:55Event JSON
{
"id": "5fc45abb4777103175954f7e676133dc1ed767e96687452e701de98890b9eb94",
"pubkey": "510c2a05dab1bae6d5d0b8d82b0da2207de52f3454c4dcf2586ca1234d18073f",
"created_at": 1728804295,
"kind": 1,
"tags": [
[
"t",
"compsci"
],
[
"t",
"machinelearning"
],
[
"proxy",
"https://mastodon.social/users/compsci_discussions/statuses/113298918291173305",
"activitypub"
]
],
"content": "[R] Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions\n\nhttps://arxiv.org/pdf/2410.06577\n\nDiscussions: https://discu.eu/q/https://arxiv.org/pdf/2410.06577\n\n#compsci #machinelearning",
"sig": "f5ea7c9d8b0b05b5405b62562570d3419d9e007a8da4ef5753a93f1fa1bbf7f237c6c2bf35d1bafba5ba85b987a4bf0d42b2718426c9ddfc55efdb1d46ff8467"
}