"length extrapolation" Papers
4 papers found
LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding
Shen Zhang, Siyuan Liang, Yaning Tan et al.
NeurIPS 2025posterarXiv:2503.04344
1
citations
Plug, Play, and Generalize: Length Extrapolation with Pointer-Augmented Neural Memory
Svetha Venkatesh, Kien Do, Hung Le et al.
ICLR 2025poster
Exploring Transformer Extrapolation
Zhen Qin, Yiran Zhong, Hui Deng
AAAI 2024paperarXiv:2307.10156
12
citations
Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation
Zhenyu He, Guhao Feng, Shengjie Luo et al.
ICML 2024poster