Pengxiao Lin

activity

20242026

most citedM

^{2}

M: Learning controllable Multi of experts and multi-scale operators are the Partial Differential Equations need

1 citations · 2 across the 7 of their papers we have counts for

collaborators

Showing 2024Show all

2 papers · 1 filter

cs.LG2024★ 1 cited

M $^{2}$ M: Learning controllable Multi of experts and multi-scale operators are the Partial Differential Equations need

Aoming Liang, Zhaoyang Mu, Pengxiao Lin +5

Learning the evolutionary dynamics of Partial Differential Equations (PDEs) is critical in understanding dynamic systems, yet current methods insufficiently learn their representat…

cs.LG2024★ 1 cited

Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing

Zhongwang Zhang, Pengxiao Lin, Zhiwei Wang +2

Transformers have shown impressive capabilities across various tasks, but their performance on compositional problems remains a topic of debate. In this work, we investigate the me…

M2M: Learning controllable Multi of experts and multi-scale operators are the Partial Differential Equations need

Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing

M $^{2}$ M: Learning controllable Multi of experts and multi-scale operators are the Partial Differential Equations need