Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@relcfp@mastodon.social
2024-12-04 05:40:08

[ February 21, 2025] Conference or similar: On Morality and Revelation: A book symposium on Amir Saemi's Morality and Revelation in Islamic Thought and Beyond (OUP, 2024) philevents.org/event/show/1298

@theawely@mamot.fr
2024-12-13 18:48:37

Excited about the new xLSTM model release. There are many well-though designs compared to transformers: recurrence (which should allows composability), gating (like Mamba & LSTM which is based on, which allows time complexity independent of the input size), state tracking (unlike Mamba & transformers). For now, these advantage aren’t apparent on benchmarks, but most training techniques are secrets, and the recent advances of LLMs evidenced that they matter a lot.