RubiConv enables boundary-respecting convolutions on packed sequences using an efficient algorithm that outperforms both attention and standard FFT baselines in speed.
Benchmark- ing and building long-context retrieval models with LoCo and M2-BERT
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RubiConv -- Efficient Boundary-Respecting Convolutions
RubiConv enables boundary-respecting convolutions on packed sequences using an efficient algorithm that outperforms both attention and standard FFT baselines in speed.