Cite
Notes
Only stored in your browser.
Attribution
MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections
arXiv 2025
Improving Transformers with Dynamically Composable Multi-Head Attention
arXiv 2024
Benchmarking and Understanding Compositional Relational Reasoning of LLMs
from 3 papers
Qingye Meng
Shengping Li
Xingyuan Yuan
Hongliang Liang
Ruikang Ni
Shihui Zheng
Xiangyu Li