fovc

Joined 10/9/2014, 5:50:32 AM has 1168 karma

Posts

NoLiMa: Long-Context Evaluation Beyond Literal Matching
by fovc on 3/10/2025, 5:52:40 PM with 0 comments
DeltaNet Explained
by fovc on 2/26/2025, 11:32:08 PM with 1 comments
Mamba-Shedder: Post-Transformer Compression for Efficient SSMs
by fovc on 2/18/2025, 2:08:57 PM with 0 comments
Reflections on 'The Bitter Lesson' (2021)
by fovc on 2/18/2025, 1:53:48 AM with 0 comments
Theoretical limitations of multi-layer Transformer
by fovc on 1/31/2025, 5:48:23 PM with 22 comments