fovc

NoLiMa: Long-Context Evaluation Beyond Literal Matching

2 points by fovc 3 months ago | 0 comments

DeltaNet Explained

2 points by fovc 4 months ago | 1 comment

Mamba-Shedder: Post-Transformer Compression for Efficient SSMs

1 point by fovc 4 months ago | 0 comments

Reflections on 'The Bitter Lesson' (2021)

1 point by fovc 4 months ago | 0 comments

Theoretical limitations of multi-layer Transformer

107 points by fovc 5 months ago | 22 comments