A recurrent-Transformer hybrid that compresses long-range context into a single RNN state vector matches segment-based Transformer baselines with fewer FLOPs on two language benchmarks and one video benchmark.
A neural probabilistic language model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Compact Recurrent Transformer with Persistent Memory
A recurrent-Transformer hybrid that compresses long-range context into a single RNN state vector matches segment-based Transformer baselines with fewer FLOPs on two language benchmarks and one video benchmark.