by Jianqiao Lu Papers
4 papers found
Conference
DeltaFormer: Unlock the state space of Transformer
Mingyu Xu, Tenglong Ao, Jiaao He et al.
NEURIPS 2025
FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
Xunhao Lai, Jianqiao Lu, Yao Luo et al.
ICLR 2025arXiv:2502.20766
62
citations
FormalAlign: Automated Alignment Evaluation for Autoformalization
Jianqiao Lu, Yingjia Wan, Yinya Huang et al.
ICLR 2025arXiv:2410.10135
10
citations
Model Merging in Pre-training of Large Language Models
Yunshui Li, Yiyuan Ma, Shen Yan et al.
NEURIPS 2025arXiv:2505.12082
21
citations