ICLR Poster "length generalization" Papers
5 papers found
A Formal Framework for Understanding Length Generalization in Transformers
Xinting Huang, Andy Yang, Satwik Bhattamishra et al.
ICLR 2025posterarXiv:2410.02140
25
citations
Generalizing Reasoning Problems to Longer Lengths
Changnan Xiao, Bing Liu
ICLR 2025poster
Language Models Need Inductive Biases to Count Inductively
Yingshan Chang, Yonatan Bisk
ICLR 2025posterarXiv:2405.20131
19
citations
Looped Transformers for Length Generalization
Ying Fan, Yilun Du, Kannan Ramchandran et al.
ICLR 2025posterarXiv:2409.15647
33
citations
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
Liliang Ren, Yang Liu, Yadong Lu et al.
ICLR 2025posterarXiv:2406.07522
118
citations