Zhanxing Zhu
4
Papers
7
Total Citations
Papers (4)
A Solvable Attention for Neural Scaling Laws
ICLR 2025
5
citations
DyCAST: Learning Dynamic Causal Structure from Time Series
ICLR 2025
1
citations
Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems
ICML 2025arXiv
1
citations
Effects of Momentum in Implicit Bias of Gradient Flow for Diagonal Linear Networks
AAAI 2025
0
citations