Poster "algorithmic tasks" Papers
4 papers found
Conference
A Formal Framework for Understanding Length Generalization in Transformers
Xinting Huang, Andy Yang, Satwik Bhattamishra et al.
ICLR 2025arXiv:2410.02140
29
citations
Looped Transformers for Length Generalization
Ying Fan, Yilun Du, Kannan Ramchandran et al.
ICLR 2025arXiv:2409.15647
41
citations
What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers
Pulkit Gopalani, Wei Hu
NEURIPS 2025arXiv:2506.13688
2
citations
Grokking Group Multiplication with Cosets
Dashiell Stander, Qinan Yu, Honglu Fan et al.
ICML 2024arXiv:2312.06581
17
citations