Sparse Transformers factorize attention to handle sequences tens of thousands long, achieving new SOTA density modeling on Enwik8, CIFAR-10, and ImageNet-64.
citation dossier
Edouard Grave, Armand Joulin, and Nicolas Usunier
6Pith papers citing it
6reference links
cs.CLtop field · 3 papers
UNVERDICTEDtop verdict bucket · 6 papers
why this work matters in Pith
Pith has found this work in 6 reviewed papers. Its strongest current cluster is cs.CL (3 papers). The largest review-status bucket among citing papers is UNVERDICTED (6 papers). For highly cited works, this page shows a dossier first and a bounded explorer second; it never tries to render every citing paper at once.
verdicts
UNVERDICTED 6representative citing papers
K-STEMIT reduces RMSE by 21% for subsurface stratigraphy thickness estimation from radar data via a knowledge-informed spatio-temporal GNN with adaptive feature fusion and physical priors from the MAR weather model.
YaRN extends the context window of RoPE-based LLMs like LLaMA more efficiently than prior methods, using 10x fewer tokens and 2.5x fewer steps while surpassing state-of-the-art performance and enabling extrapolation beyond fine-tuning lengths.
Universal Transformers combine Transformer parallelism with recurrent updates and dynamic halting to achieve Turing-completeness under assumptions and outperform standard Transformers on algorithmic and language tasks.
A visual transformer model trained on IRIS inversions predicts chromospheric temperature and density from SDO data with correlations around 0.8 on 80% of test cases.
Pith review generated a malformed one-line summary.
citing papers explorer
-
Universal Transformers
Universal Transformers combine Transformer parallelism with recurrent updates and dynamic halting to achieve Turing-completeness under assumptions and outperform standard Transformers on algorithmic and language tasks.