Author

Kang An

1 paper indexed here

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.

#artificial intelligence May 2026

Demystifying Manifold Constraints in LLM Pre-training

By controlling the update-to-weight ratio, constrained training significantly alleviates update cancellation, empirically demonstrating that MACRO is robust to low-precision computation and competitive with existing algorithms for standard LLM pre-training.

Kang An, Jiaxiang Li, Donald Goldfarb et al. · arXiv.org · 1 citation