Sparse Token Transformer with Attention Back Tracking

Heejun Lee, Minki Kang, Youngwan Lee, Sung Ju Hwang

2/12/2026

No official code found. Best implementation: gmlwns2000/sttabt (8 stars, last commit 2023-03-15).

Semantic Scholar

Code Implementations(1)

gmlwns2000/sttabtCommunity67%

[ICLR2023] Official code of Sparse Token Transformer with Attention Back-Tracking

80TeX, ShellNov 22, 20213 years ago

sparsetransformers

Cite this paper

@article{lee2026sparse,
  title  = {Sparse Token Transformer with Attention Back Tracking},
  author = {Heejun Lee and Minki Kang and Youngwan Lee and Sung Ju Hwang},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:8b16dc5b4c0728147eef1647a6ab7f786333b76c},
  journal = {ICLR 2023 2023}
}

Sparse Token Transformer with Attention Back Tracking

Code Implementations(1)

Cite this paper

Discussion