Self-pretraining improves Transformer sequence classification by enabling learning of proximity-biased attention from positional encodings that label supervision alone cannot easily acquire from random starts.
Title resolution pending
3 Pith papers cite this work, alongside 6 external citations. Polarity classification is still indexing.
3
Pith papers citing it
6
external citations · external index
fields
cs.LG 3representative citing papers
Gated linear attention Transformers achieve competitive language modeling results with linear-time inference, superior length generalization, and higher training throughput than Mamba.
Rotating value embeddings along with keys and queries (RoVE) converts RoPE attention into a block-Toeplitz attentive convolution and yields consistent gains across 124M and 354M GPT-2 models.
citing papers explorer
-
Towards Understanding Self-Pretraining for Sequence Classification
Self-pretraining improves Transformer sequence classification by enabling learning of proximity-biased attention from positional encodings that label supervision alone cannot easily acquire from random starts.
-
Gated Linear Attention Transformers with Hardware-Efficient Training
Gated linear attention Transformers achieve competitive language modeling results with linear-time inference, superior length generalization, and higher training throughput than Mamba.
-
RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways
Rotating value embeddings along with keys and queries (RoVE) converts RoPE attention into a block-Toeplitz attentive convolution and yields consistent gains across 124M and 354M GPT-2 models.