Da Xiao
3
Papers
13
Total Citations
Papers (3)
MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections
ICML 2025arXiv
9
citations
Benchmarking and Understanding Compositional Relational Reasoning of LLMs
AAAI 2025arXiv
4
citations
Improving Transformers with Dynamically Composable Multi-Head Attention
ICML 2024
0
citations