Author

Qi-Bang Liu

h-index 9 View on Semantic Scholar

We have 1 of 28 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Disentangling Attention in Deep Operator Learning: A Controlled Study of Data-Driven and Physics-Informed Architectures

Overall, query-dependent cross-attention is the most reliable mechanism, whereas branch self-attention is most useful for large, spatially complex functional inputs, whereas branch self-attention is most useful for large, spatially complex functional inputs.

Amar Alem Koric, Qi-Bang Liu, S. Koric · 0 citations