← Search

Zhihao Teng

2 accepted papers

2025

Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling

ICML 2025poster

Despite the success of Transformers, handling longer contexts remains challenging due to the limited length generalization and quadratic complexity of self-attention, which often requires post-training with a larger attention window, significantly increasing computational and memory costs. In this p…

Cited by 0SourcePDFScholar